CHAPTER ONE

INTRODUCTION

1.1 Background to the study

Fraud prevention has emerged as a top priority in the global banking and financial sector due to

the persistent rise in sophisticated fraudulent activities. Fraud is generally defined as a deliberate

act of deception intended to gain an unfair or unlawful advantage, often resulting in financial

losses for individuals or organizations (Okoye & Akamobi, 2009). In the banking sector, fraud

can take many forms, including identity theft, phishing attacks, falsified financial documents,

unauthorized transactions, and internal collusion. These fraudulent activities not only undermine

public trust in the banking system but also impose significant financial, reputational, and

operational costs on financial institutions (Albrecht, Albrecht, & Zimbelman, 2011).

The impact of fraud is particularly severe in the countries around the world, specifically Nigeria,

where weak internal control systems, low financial literacy, and limited regulatory enforcement

increase the vulnerability of banks to financial crimes. Reports from the Nigeria Deposit

Insurance Corporation (NDIC) and Central Bank of Nigeria (CBN) consistently indicate a

worrying trend in the number and value of fraud cases recorded in commercial banks annually

(NDIC, 2022). According to global statistics, consumers lost over $12.5 billion to fraud in 2024

alone—a 25% increase from the previous year—with investment scams accounting for $5.7

billion of those losses (FTC, 2025). Such alarming figures emphasize the urgency for more

effective fraud prevention measures.

Traditionally, banks have relied on manual auditing, staff training, segregation of duties, and

internal control mechanisms to detect and prevent fraud. However, these methods have proven

increasingly inadequate in addressing the speed and complexity of modern fraudulent activities.

1
As fraudsters become more technologically advanced, there is a growing consensus among

scholars and practitioners that traditional tools alone cannot provide the needed level of

protection in today’s financial environment (Bolton & Hand, 2002). Consequently, banks must

turn to more dynamic, automated, and intelligent systems for combating fraud.

Accounting Information Systems (AIS) serve as the backbone of financial record keeping,

monitoring, and reporting within banks. AIS is a computer-based system that collects, processes,

and stores financial data to support decision-making and ensure accountability (Romney &

Steinbart, 2018). When effectively deployed, AIS enhances internal control, improves

transaction accuracy, and reduces the risk of financial misstatement. However, as fraud risks

evolve, it is imperative for AIS to be strengthened with advanced technologies that can predict

and respond to potential fraud threats in real time.

This leads to the increasing adoption of Artificial Intelligence (AI) as a transformative tool in the

fight against financial fraud. In 1955, Hubbard, Simon, Allan, Newell, and John Shaw developed

the Logic Theorist program, which was the first example of artificial intelligence. This early AI

program was intended to stimulate human problem-solving abilities based on the principles of

logic. Over the subsequent two decades, advancements in AI flourished as scientists gained a

better understanding of computers, and as computer storage capacity expanded. This progress

was of great benefit to accountants because it reduced the amount of effort required to process

large volumes of data on a daily basis. As a result, AI became an indispensable tool in

accounting and data [Link] refers to the use of computer systems that can simulate

human intelligence by learning from data, recognizing patterns, and making decisions with

minimal human intervention (Russell & Norvig, 2016).

2
In fraud prevention, AI can be embedded into AIS to perform tasks such as anomaly detection,

predictive analytics, and automated alert systems. These intelligent capabilities allow banks to

detect irregularities in financial transactions, assess fraud risk, and respond promptly to

suspicious activities (Ngai et al., 2011).

AI applications such as machine learning algorithms, neural networks, and natural language

processing have already demonstrated success in enhancing fraud detection and prevention in

global banking systems (Ravisankar et al., 2011). These technologies enable banks to analyze

massive datasets, identify hidden patterns of fraudulent behavior, and adapt their fraud

prevention mechanisms continuously. Unlike traditional methods, AI-driven fraud detection

systems are not limited by predefined rules but evolve as they learn from new data.

Despite these advantages, the adoption of AI in fraud prevention remains limited in many

commercial banks in Nigeria, especially in Maiduguri, Borno State. Factors such as high

implementation costs, lack of technical expertise, data security concerns, and resistance to

innovation hinder the integration of AI into existing accounting systems (Afolabi & Oladipo,

2021). Furthermore, there is limited empirical research on how commercial banks in Maiduguri

are utilizing AI to enhance AIS for fraud prevention.

Therefore, this study seeks to examine the role of Artificial Intelligence in enhancing Accounting

Information Systems for fraud prevention in commercial banks in Maiduguri, Borno State. The

study will investigate the level of AI adoption, evaluate its effectiveness, and explore the barriers

hindering its implementation. Findings from this research are expected to provide valuable

insights to financial institutions, regulators, and policymakers on how to leverage AI

technologies to strengthen fraud prevention efforts and build more resilient banking systems.

3
1.2 Statement of the problem

Fraud remains a critical concern in the global banking sector, especially within developing

economies like Nigeria. Financial fraud, including cybercrime, identity theft, internal

manipulation, and unauthorized transactions, leads to significant financial losses and erodes

public trust in financial institutions (Albrecht et al., 2011). Despite efforts by commercial banks

to implement internal controls, periodic audits, and regulatory compliance, fraudulent activities

continue to increase in complexity and scale. Reports from regulatory bodies such as the NDIC

and CBN indicate a rising trend in banking fraud cases across the country, with Maiduguri,

Borno State, not being an exception (NDIC, 2022). Traditional fraud detection systems have

proven inadequate in addressing these sophisticated schemes, highlighting a gap in proactive and

accurate fraud detection.

While Artificial Intelligence (AI) has shown promising results in fraud detection and prevention

globally, there is limited research and practical insight into how commercial banks in Maiduguri

have adopted and implemented AI into their Accounting Information Systems (AIS). It is unclear

to what extent these banks are using AI technologies such as machine learning, predictive

analytics, or anomaly detection for fraud prevention. Moreover, there is insufficient data on the

challenges and barriers faced by these banks in integrating AI, such as infrastructural constraints,

cost implications, technical expertise, and regulatory readiness. These unknowns hinder our

understanding of the role AI currently plays in enhancing fraud detection in the region.

Understanding how AI can be applied to AIS for fraud prevention is essential for improving the

efficiency, transparency, and reliability of banking systems in Maiduguri. By exploring these

unknowns, this study can reveal whether AI tools are being underutilized and if banks are

4
missing opportunities to strengthen their internal control systems. More importantly, uncovering

these gaps can help banks develop strategic responses to fraud, reduce operational risks, protect

customer funds, and build long-term public trust. It also contributes valuable knowledge to

academic literature and supports policymaking that promotes AI-driven innovations in financial

regulation and digital transformation.

To bridge this knowledge gap, this study will employ a cross-sectional research design,

collecting data from commercial banks operating in Maiduguri, Borno State. The research will

involve surveys and interviews with bank employees, auditors, forensic accountants, and

financial managers to assess their knowledge, experience, and perception of AI-powered AIAs

for fraud prevention.

1.3 Objective of the study

The main objective of this study is to assess the role of Artificial Intelligence (AI) in enhancing

accounting information system (AIS) on fraud prevention in commercial banks in Maiduguri,

Borno State.

Specifically, the study aims to:

1. examine the extent of AI adoption in accounting information systems (AIS) in fraud detection

in commercial banks in Maiduguri, Borno State.

2. evaluate the challenges associated with implementing AI-deriving fraud prevention

mechanisms in commercial banks.

3. assess the effectiveness of AI in detecting and mitigating fraudulent activities in commercial

banking operations.

5
4. explore the regulatory and operational factors influencing the integration of AI in fraud

prevention strategies.

1.4 Research Questions

To achieve the research objectives, the following research questions will be addressed:

1. How does Artificial Intelligence (AI) enhance the effectiveness of accounting information

systems (AIS) in commercial banks in Maiduguri, Borno State?

2. What are the key challenges in integrating AI-driven accounting information systems for fraud

prevention?

3. How do AI-powered systems improve fraud detection and prevention in commercial banks?

4. To what extent does AI contribute to the accuracy and efficiency of financial reporting in

commercial banks?

1.5 Research Hypothesis

H01 Artificial intelligence does not significantly enhance the effectiveness of accounting

information systems in commercial banks in Maiduguri, Borno State.

H02. AI-driven accounting information systems do not significantly improve fraud detection and

prevention in commercial banks.

H03. Artificial intelligence (AI) does not significantly contribute to the accuracy and efficiency of

financial reporting in commercial banks.

6
1.6 Significance of the study

This study holds significant relevance for multiple stakeholders including money deposit banks,

regulatory bodies, financial analysts, and academic researchers.

Firstly, for commercial banks operating in Maiduguri, Borno State, this research will provide

insights into how Artificial Intelligence (AI) can enhance accounting information systems to

mitigate fraud. The findings will assist bank managers and IT professionals in making informed

decisions on AI-deriving fraud detection and prevention mechanisms.

Secondly, regulatory bodies such as the Central Bank of Nigeria (CBN) and the Nigerian Deposit

Insurance Corporation (NDIC) can benefit from this study by understanding the extent to which

AI can be integrated into compliance measures. This will support the formulation of policies that

encourages responsible AI adoption in the banking sector while maintaining financial security

and customer trust. Additionally, financial analysts and auditors can leverage the study's findings

to refine their auditing strategies. By understanding the role of AI in fraud detection, auditors can

implement more effective risk assessment procedures, reducing the incidence of undetected

fraudulent activities.

From an academic perspective, this research contributes to the existing literature on artificial

intelligence (AI) and accounting information systems (AIS). It serves as a valuable resource for

future researchers interested in exploring the intersection of artificial intelligence, financial fraud

prevention, and accounting technology advancements.

1.7 Scope of the study

This study focuses on examining the role of Artificial Intelligence (AI) in enhancing accounting

information systems (AIS) on fraud prevention in commercial banks operating in Maiduguri,

7
Borno State. It aims to analyze how AI-driven technologies such as machine learning, predictive

analytics, and automation improved fraud detection, financial reporting accuracy, and overall

system security. The study will target selected commercial banks within Maiduguri to assess the

adoption, effectiveness, and challenges of AI implementation in their AIS. Data will be collected

from bank staffs, IT professionals, and auditors through surveys and interviews to gain insights

into the practical application of AI in fraud prevention.

The period covered by this study is from 2019 to 2024, ensuring that the analysis reflects recent

trends, technological advancements, and evolving fraud patterns relevant to the current banking

landscape.

8
 CHAPTER TWO

LITERATURE REVIEW

2.1 Conceptual Issues

2.1.1 Concept of Fraud and Fraud Prevention

Fraud has been extensively conceptualized in academic and professional literature. The

Association of Certified Fraud Examiners (ACFE, 2022) defines fraud as "the deliberate use of

misrepresentation or concealment to secure unlawful financial or personal gain." Similarly, under

the Fraud Act 2006 (UK), fraud constitutes "a criminal offense involving deception, false

representation, or abuse of position for pecuniary or proprietary advantage.

From an organizational perspective, Okoye and Akamobi (2009) characterize fraud as "a

premeditated manipulation of truth or factual records by internal or external actors to derive

undue benefits. Generally, fraud is deliberate deception, often involving mispresentation or

concealment of information, with the intent to gain an unfair or unlawfull advantages or benefits

at the expense of another.

Collectively, these definitions highlights the following four (4) critical elements:

Intentionality: fraud is not accidental or unintentional but rather it requires conscious decision

to deceive.

Deception: fraud involves misleading or tricking others.

Unfair advantage: the goal of fraud is to gain something unlawfully or unfairly.

Harm: fraud can either cause financial loss, emotional distress, or damage of reputation.

Fraud is typically categorized into three major typologies: financial statement fraud, asset

misappropriation, and corruption.

9
 Financial Statement Fraud

Involves deliberate falsification or manipulation of financial records to mislead stakeholders.

This may include overstating revenues, understating liabilities, or manipulating earnings.

Asset Misappropriation

This is the most common type of fraud, often involving theft or misuse of an organization’s

assets, such as cash theft, cheque forgery, and unauthorized use of company resources.

Corruption

Involves abuse of power for personal gain, including bribery, kickbacks, and conflicts of interest.

Emerging forms such as cyber fraud, which includes identity theft, phishing, malware attacks,

and ATM skimming, have become increasingly prevalent with the digitization of banking

operations (Aliyu & Yusuf, 2023; Musa & Raji, 2022).

Fraud prevention represents an integrated organizational strategy designed to proactively deter,

detect, and mitigate fraudulent activities through multilayered controls. It involves a systematic

approach that combines policies, procedures, and technologies aimed at minimizing the

opportunities for fraud to occur within an organization. According to Obara and Nangih (2017),

fraud prevention goes beyond simply responding to fraudulent acts after they occur; instead, it

emphasizes proactive measures such as ethics training for employees, effective internal control

systems, the use of modern technological tools, and periodic audit procedures. Building on the

perceptions of Obara and Nangih, it is evident that fraud prevention within organizations

encompasses several key dimensions. Employee ethics training serves as a foundational element,

as it fosters a culture of integrity and ethical responsibility among staff members. When

employees are adequately informed about organizational ethical expectations and the

consequences of engaging in fraudulent behavior, the likelihood of collusion or misconduct is

10
significantly reduced. Furthermore, the establishment of robust internal control systems,

including checks and balances, segregation of duties, authorization protocols, and regular

reconciliations, functions as both preventive and detective mechanisms against fraud. In addition,

technological interventions have become increasingly vital in contemporary fraud prevention

strategies. The integration of artificial intelligence (AI), data analytics, forensic accounting tools,

and real-time monitoring systems enhances an organization’s capacity to identify anomalies,

detect irregular patterns, and respond swiftly to potential threats. Technology, therefore, enables

the development of early warning systems that play a critical role in deterring fraudulent

activities. Finally, audit practices, both internal and external, provide an additional layer of

assurance by evaluating the adequacy and effectiveness of existing controls, identifying

weaknesses, and recommending necessary improvements. Through these audits, accountability

and transparency are reinforced across all levels of the organization, thereby strengthening the

overall fraud prevention framework.

In essence, fraud prevention is not a one-time measure but an ongoing commitment that requires

collaboration across departments, continuous evaluation, and adaptation to emerging fraud risks.

The goal is to create a high-integrity environment where the cost and risk of committing fraud far

outweigh the perceived benefits, thereby reducing its occurrence.

2.1.2 Historical Background of Fraud in Banking.

Fraud in banking is not a recent phenomenon, it has existed since the inception of trade and

financial transactions. However, its methods and scale have evolved alongside advancements in

banking systems. In Nigeria, bank fraud traces back to the post-independence era (1960s-1970s),

when manual banking processes were dominant. Fraudulent activities during this period were

11
largely internal, involving forgery, cheque fraud, and account manipulation by bank employees

or collaborators (Adeniran & Adeyemo, 2017).

The introduction of automated banking systems in the 1980s and 1990s marked a shift in fraud

patterns. While digitalization improved efficiency, it also opened new avenues for fraudsters.

The Nigerian banking sector witnessed high-profile fraud cases, including insider abuse, loan

scams, and money laundering. The lack of stringent regulations and weak enforcement

mechanisms further worsen the problem (Central Bank of Nigeria [CHN], 2014).

With the rapid adoption of electronic banking (e-banking) in the 2000s, fraud migrated to digital

platforms. The CBN's cashless policy (introduced in 2012) accelerated online transactions but

also increased cyber fraud risks. Fraudsters exploited vulnerabilities in online banking, mobile

banking, and card transactions, leading to phishing scams, identity theft, and unauthorized fund

transfers (EFCC, 2020).

2.1.4 Accounting Information Systems (AIS)

An Accounting information System (AIS) is a structured framework that integrates people,

procedures, software, and data to collect, process, store, and report financial transactions

(Romney & Steinbart, 2018), In commercial banking, AIS constitute the technological and

procedural infrastructure that enables them to maintain operational integrity and strategic

decision making.

In a nutshell, Accounting information system (AIS) is a system that businesses uses to collect,

store, manage, process, retrieve and reports its financial data to produce an information that can

be used for decision making. It tracks all accounting and business activity for a company and

which consists of various interdependent component.

12
In Nigeria’s commercial banking sector, the Accounting Information System (AIS) performs

three critical institutional functions that collectively support the integrity, efficiency, and

sustainability of banking operations.

Firstly, AIS plays a vital role in financial stewardship by maintaining comprehensive and

accurate records of all transactional data. This includes the systematic documentation of

customer accounts, loan portfolios, interbank settlements, and other financial activities that form

the backbone of banking operations. Through this function, the AIS ensures accountability,

transparency, and traceability of every financial transaction, thereby providing management with

reliable financial information for effective control and decision-making. The system also

supports compliance with statutory reporting requirements by enabling banks to produce timely

and verifiable financial statements in accordance with regulatory standards.

Secondly, the AIS serves as an instrument of regulatory assurance. In a highly regulated sector

like banking, compliance with the guidelines and standards of the Central Bank of Nigeria

(CBN) and other regulatory bodies is essential. AIS facilitates this by generating automated audit

trails and compliance reports that track all activities within the system. These audit trails enhance

transparency and make it possible for both internal and external auditors to verify the accuracy

and legitimacy of financial records. Furthermore, by automating regulatory reporting, AIS

minimizes human error, reduces delays, and ensures that the bank adheres to financial laws, anti-

money laundering regulations, and corporate governance principles.

Thirdly, AIS significantly contributes to decision-making within the banking sector by providing

predictive analytics and data-driven insights that inform strategic and operational decisions.

Using advanced analytical tools, the AIS helps in credit risk modeling, liquidity management,

and forecasting financial trends. These analytical capabilities enable management to identify

13
potential risks early, assess customer creditworthiness, and optimize resource allocation. In

addition, AIS supports management in evaluating profitability, performance efficiency, and

customer behavior patterns, all of which are crucial for achieving competitive advantage and

sustaining growth in an increasingly digital banking environment.

In summary, the AIS in Nigeria’s commercial banking institutions is not merely an accounting

tool but a strategic framework that integrates financial management, regulatory compliance, and

data-driven decision-making into a unified system.

[Link] Core Components of Accounting Information System (AIS)

Generally, an Accounting Information System (AIS) comprises six fundamental components that

collectively ensure the accurate recording, processing, and reporting of financial information

within an organization. These components work interdependently to enhance transparency,

promote accountability, and strengthen internal controls, particularly in the banking sector where

reliability and security of financial data are paramount.

The human element forms the backbone of every AIS, representing the individuals who design,

develop, operate, and maintain the system. These include accountants, system analysts, auditors,

information technology experts, and end users who interact with the system daily. The efficiency

and effectiveness of any accounting system depend heavily on the competence, ethical

disposition, and diligence of these personnel. Their understanding of accounting procedures,

combined with technological proficiency, ensures that financial data are properly processed and

that the output generated from the system remains accurate and reliable.

Equally important are the procedures and instructions that guide how accounting transactions are

collected, processed, and stored. These procedures define the flow of data through the system

14
and ensure consistency, accuracy, and compliance with accounting principles and organizational

policies. Well-structured procedures minimize errors, enhance control over financial operations,

and ensure that users follow standardized methods when handling financial information.

The data component represents the raw material of the accounting information system. It

encompasses all the relevant financial and non-financial information generated from the

organization’s business activities, such as transactions, payments, receipts, sales, purchases, and

other economic events. High-quality and reliable data are critical to ensure the validity of

accounting outputs, as inaccurate or incomplete data can distort decision-making and create

opportunities for manipulation or fraud.

Another vital component is the software used to process accounting data into meaningful

information. The software executes functions such as data entry, classification, posting to

ledgers, computation of balances, and report generation. In contemporary banking operations,

accounting software has evolved from simple bookkeeping tools to highly sophisticated

applications integrated with Artificial Intelligence (AI), data analytics, and cloud-based

computing technologies. These modern systems enable real-time processing, automated fraud

detection, and improved financial decision-making.

The technological infrastructure, which includes computers, servers, storage devices, and

communication networks, provides the physical foundation upon which the entire accounting

system operates. A well-established IT infrastructure enhances operational efficiency, enables

quick access to information, and facilitates the smooth exchange of data across different

departments and branches of a bank. It ensures that transactions are processed promptly and

securely, supporting the bank’s digital transformation agenda.

15
Lastly, internal control and security measures serve as protective mechanisms for both the

accounting data and the system itself. They involve the use of access controls, passwords,

encryption, firewalls, audit trails, and segregation of duties to safeguard information from

unauthorized access, manipulation, or loss. Effective internal controls reinforce accountability

and data integrity, ensuring that financial reports are credible and compliant with regulatory

standards.

In essence, the integration of these six components—human resources, procedures, data,

software, infrastructure, and internal control mechanisms—forms the core framework of a sound

accounting information system. Their harmonious operation promotes accuracy, efficiency, and

transparency in financial reporting, which are indispensable qualities for fraud prevention and

sustainable banking operations in Nigeria’s commercial banking sector.

[Link] Vulnerabilities of Modern AIS to Fraudulent Activities

Despite their numerous advantages, modern Accounting Information Systems (AIS) are not

immune to risks and vulnerabilities that expose organizations, especially commercial banks, to

fraudulent activities. As financial institutions continue to embrace digital transformation and

automation, the complexity of these systems has also increased, thereby creating new

opportunities for both internal and external actors to exploit weaknesses within the system. These

vulnerabilities, if not properly managed, can compromise the reliability, confidentiality, and

integrity of financial information — the very pillars upon which effective accounting and fraud

prevention depend.

One of the most prominent vulnerabilities within modern AIS is data manipulation. This occurs

when authorized users intentionally alter, falsify, or delete financial data for personal gain or to

16
conceal fraudulent transactions. Insiders such as accountants, cashiers, or IT officers with

privileged system access may exploit their positions to modify financial records, adjust balances,

or erase digital audit trails. Such actions distort the accuracy of financial reports and may result

in significant financial losses. Data manipulation is particularly dangerous because it often goes

unnoticed for extended periods unless robust audit trails, system monitoring, and segregation of

duties are in place.

Another major vulnerability is unauthorized access to accounting databases and financial

applications. Weak authentication mechanisms, such as the use of easily guessed passwords,

shared login credentials, or unencrypted communication channels, can provide cybercriminals

with the opportunity to penetrate internal systems. Once inside, attackers may extract sensitive

information such as customer account details, alter transactions, or disable control mechanisms.

The growing trend of remote banking and the integration of AIS with online banking platforms

further amplifies these risks. Without stringent cybersecurity measures like multi-factor

authentication, intrusion detection systems, and continuous monitoring, financial institutions

remain susceptible to breaches that could undermine public trust and regulatory compliance.

A third vulnerability lies in transactional anomalies, which refer to unusual or irregular

transaction patterns that deviate from normal operational behavior. Fraudsters often exploit

system loopholes, software bugs, or design weaknesses to execute unauthorized transfers,

duplicate transactions, or create fictitious accounts. In many cases, these anomalies arise from

poorly configured systems or inadequate internal controls that fail to flag suspicious activities in

real time. Although modern AIS are increasingly equipped with automated anomaly-detection

features, these tools are only as effective as the data and algorithms upon which they rely.

17
These vulnerabilities are further compounded by factors such as inadequate employee training,

poor data governance, and weak regulatory oversight. When organizations fail to continuously

update their systems or neglect to train staff on emerging fraud schemes, the likelihood of system

abuse increases. Additionally, as financial institutions integrate third-party applications and

cloud-based technologies, new risks emerge concerning data sharing, vendor reliability, and

system interoperability.

In conclusion, while AIS remains indispensable for efficient financial management and fraud

prevention, its susceptibility to manipulation, unauthorized access, and transactional

irregularities cannot be overlooked. Recognizing these vulnerabilities is the first step toward

developing stronger internal controls, investing in advanced cybersecurity technologies, and

cultivating a culture of vigilance and ethical responsibility within Nigeria’s commercial banking

sector.

These vulnerabilities are compounded in systems lacking up-to-date cybersecurity measures

(Umar & Bello, 2023).

2.1.5 Artificial Intelligence (AI) Fundamentals

[Link] Definition and Key Branches of AI

Artificial Intelligence (AI) is a prominent branch of computer science dedicated to creating

machines and systems that can perform tasks which traditionally require human intelligence.

These tasks include learning, reasoning, problem-solving, perception, and understanding natural

language (Russell & Norvig, 2016). AI enables computers to simulate intelligent behavior and

make decisions based on data, patterns, and programmed algorithms.

18
In the field of accounting, AI has revolutionized how financial information is processed and

utilized. It plays a vital role in enhancing the efficiency and effectiveness of Accounting

Information Systems (AIS), particularly in the areas of fraud detection, risk management,

auditing, and financial reporting. AI systems can analyze vast amounts of transactional data at

high speeds, uncover hidden anomalies, detect suspicious patterns, and automate decision-

making processes with greater accuracy and consistency than traditional manual methods.

Key Branches of Artificial Intelligence

Artificial Intelligence (AI) comprises various specialized branches, each contributing uniquely to

the advancement of intelligent systems capable of mimicking human reasoning, learning, and

decision-making. In the context of accounting and fraud prevention, these branches work

together to enhance the analytical capacity of Accounting Information Systems (AIS), improve

fraud detection accuracy, and ensure stronger internal control mechanisms. The four principal

branches of AI that are most relevant to modern accounting and banking operations are Machine

Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), and Expert Systems.

Machine Learning (ML) represents one of the most fundamental and widely adopted branches of

AI. It focuses on developing algorithms that enable computers to learn automatically from

historical data and improve their performance over time without explicit programming. Through

exposure to large datasets, machine learning systems can identify hidden patterns and

relationships, allowing them to make informed predictions and classifications. In the field of

accounting, ML plays a crucial role in fraud detection and prevention by analyzing vast amounts

of transaction data to recognize deviations from established norms. For instance, ML algorithms

can learn what constitutes a normal transaction pattern and flag any behavior that appears

inconsistent, such as unusual account activity or atypical cash flows. Moreover, the adaptive

19
nature of ML enables continuous improvement, as the model becomes more accurate with every

new dataset it processes. This makes it invaluable for commercial banks where fraud tactics

constantly evolve.

Deep Learning (DL), a specialized subset of machine learning, utilizes artificial neural networks

composed of multiple layers — often referred to as deep architectures — to model and interpret

highly complex relationships within data. Deep learning algorithms are designed to mimic the

human brain’s ability to recognize patterns, enabling systems to analyze massive volumes of

structured and unstructured data. This technology is particularly useful for detecting

sophisticated financial frauds that involve concealed or multi-layered schemes. In practice, deep

learning has proven effective in identifying suspicious behavioral trends and transaction

anomalies that may not be apparent through conventional analytical methods. Additionally, DL

techniques are increasingly employed to analyze unstructured data such as digital images,

scanned invoices, and voice records, which can serve as supporting evidence during financial

investigations or forensic audits. Its ability to process large datasets in real-time also enhances

the responsiveness of fraud monitoring systems in modern banks.

Natural Language Processing (NLP) is another vital branch of AI that enables computers to

understand, interpret, and generate human language in both spoken and written forms. In the

accounting and financial domains, NLP is used to analyze vast amounts of textual data to extract

meaningful insights and detect potential red flags. For instance, NLP algorithms can be applied

to audit logs, management emails, financial statements, or whistleblower reports to identify

patterns of misconduct or linguistic cues that suggest fraudulent intent. Furthermore, NLP can

assist in compliance monitoring by scanning legal documents and regulatory updates to ensure

that accounting practices align with current standards. By automating the analysis of

20
unstructured textual information, NLP reduces manual review time and improves the accuracy of

detecting irregularities that may escape human attention.

Expert Systems constitute another significant branch of AI designed to emulate the decision-

making processes of human specialists in specific domains. These systems are built upon a

knowledge base of facts, experiences, and predefined rules, combined with an inference engine

that applies logical reasoning to reach conclusions. In the context of accounting and fraud

prevention, expert systems replicate the reasoning of auditors, compliance officers, or forensic

accountants. They can automatically flag transactions or financial entries that violate established

accounting principles, organizational policies, or regulatory standards. For example, if a

transaction exceeds a certain approval limit or fails to meet reconciliation requirements, the

expert system can immediately generate alerts for further review. This capability helps

institutions maintain consistent decision-making and enhances transparency and accountability in

financial operations.

In summary, the integration of these AI branches — Machine Learning, Deep Learning, Natural

Language Processing, and Expert Systems — is revolutionizing fraud prevention in the banking

industry. Together, they empower Accounting Information Systems to function with greater

precision, speed, and autonomy, allowing financial institutions to detect, prevent, and respond to

fraudulent activities more effectively than ever before.

The integration of these AI branches into accounting systems is transforming the fraud detection

landscape in commercial banks. AI-powered fraud prevention tools are capable of real-time

monitoring of financial activities, automatic anomaly detection, and predictive modeling to

anticipate potential threats. According to Alrama and Alras (2023), the use of AI technologies in

21
banking institutions significantly improves the detection of fraudulent behaviors and enhances

internal control mechanisms.

[Link] Core Concepts in Machine Learning

Machine Learning (ML) stands as one of the most practical and widely applied subsets of

Artificial Intelligence (AI), especially in the fields of accounting, auditing, and fraud prevention.

It equips computer systems with the ability to learn from data and improve their performance

without explicit programming instructions. This adaptive capability makes ML invaluable in

dynamic environments such as commercial banking, where new fraud patterns constantly

emerge. In the context of fraud prevention, ML systems can be trained to analyze large volumes

of financial transactions, detect anomalies, and predict potentially fraudulent activities based on

learned behaviors. The core concepts of ML revolve around three main learning paradigms —

supervised learning, unsupervised learning, and reinforcement learning. Each paradigm

contributes distinct analytical capabilities that enhance the detection and prevention of financial

fraud within Accounting Information Systems (AIS).

Supervised Learning is the most commonly applied ML approach in fraud detection. It involves

training algorithms on labeled datasets — that is, data where both input variables and

corresponding outcomes are known. For example, a bank might use historical transaction records

labeled as either “fraudulent” or “non-fraudulent” to train an ML model. The algorithm learns

the distinguishing characteristics of fraudulent transactions and applies this knowledge to predict

and classify new cases. Techniques such as decision trees, random forests, and support vector

machines (SVMs) are typical examples of supervised learning models used in banking and

accounting. The strength of supervised learning lies in its accuracy and efficiency when adequate

22
and high-quality labeled data are available. This method enables organizations to quickly

identify known fraud patterns, minimize false alarms, and improve overall risk management

practices.

Unsupervised Learning, on the other hand, operates on unlabeled data — where outcomes or

categories are not predefined. This makes it particularly useful in detecting unknown or

emerging fraud schemes that have not yet been observed or documented. In this approach, the

ML algorithm identifies natural groupings or patterns within the data, allowing it to spot

transactions or behaviors that deviate from the norm. For instance, clustering algorithms such as

K-Means or Hierarchical Clustering can segment customers or transactions into groups based on

shared characteristics. Any transaction that falls outside expected clusters may signal potential

fraud. This proactive capability allows banks to discover previously undetected fraudulent

behaviors and enhance their internal surveillance systems. Unsupervised learning is therefore

essential in modern fraud detection environments, where fraudsters continually evolve their

tactics to bypass existing controls.

Reinforcement Learning (RL) represents a more dynamic and interactive form of machine

learning. In this paradigm, models learn through trial and error by interacting with an

environment and receiving feedback in the form of rewards or penalties. Over time, the system

optimizes its behavior to maximize cumulative rewards, leading to continuous improvement in

decision-making. In the context of fraud prevention, reinforcement learning can be employed to

optimize fraud detection thresholds, allocate investigative resources, or enhance real-time

decision-making in transaction monitoring systems. For example, an RL algorithm may learn to

adjust fraud alert sensitivity levels automatically based on feedback from investigators, thereby

reducing false positives while maintaining strong fraud detection performance.

23
In summary, these three learning paradigms — supervised, unsupervised, and reinforcement

learning — provide the foundational framework through which ML supports fraud detection and

prevention in banking institutions. While supervised learning is ideal for identifying known fraud

cases using labeled datasets, unsupervised learning excels in discovering new and hidden fraud

patterns. Reinforcement learning, meanwhile, adapts dynamically to ever-changing fraud

environments. Together, they make machine learning a critical driver of intelligent, adaptive, and

proactive fraud prevention systems in modern accounting and finance.

Commercial banks use these methods to train models capable of identifying both known and

emerging fraud patterns (Ahmed et al., 2022).

[Link] Data Requirements and Preprocessing for AI Applications

Artificial Intelligence (AI) systems, particularly those applied in accounting and fraud detection,

rely fundamentally on data quality, quantity, and structure. The effectiveness of any AI-driven

model depends largely on the nature of the data it processes, as the model’s learning and

prediction accuracy are only as good as the information it receives. In the context of Accounting

Information Systems (AIS), high-quality data serves as the foundation for building robust,

intelligent, and adaptive systems capable of identifying fraudulent patterns and preventing

financial irregularities within commercial banks.

AI-based fraud detection systems depend heavily on large, diverse, and representative datasets

that capture various aspects of banking operations. Such datasets typically include transaction

logs, user behavioral histories, system access logs, and audit trails. Transaction logs provide

detailed information on the flow of funds, including timestamps, transaction types, account

identifiers, and amounts — all crucial for detecting anomalies. User behavior data captures

patterns such as login frequency, geographic access locations, and device identifiers, which can

24
help differentiate between legitimate and suspicious activity. System access logs, on the other

hand, record administrative or employee actions within the AIS, providing critical insights into

insider threats and unauthorized manipulations. Collectively, these datasets form a

comprehensive foundation for AI models to detect both internal and external frauds.

However, raw data alone is not sufficient. For AI applications to function effectively, data must

undergo a systematic preprocessing phase to ensure its reliability, consistency, and readiness for

analytical modeling. This phase involves several key steps:

Data Cleaning – This is the initial and most essential stage of preprocessing. It involves

identifying and rectifying errors, missing values, duplicate records, and inconsistencies that may

distort analytical results. For example, a missing transaction timestamp or duplicate entry could

mislead a machine learning model into producing false fraud alerts.

Data Normalization – This process standardizes data values within a specific range or format to

ensure uniformity across datasets. Since financial data often come in varied scales — such as

currency amounts, time durations, or categorical codes — normalization ensures that all

variables contribute proportionately to model training, preventing bias toward variables with

larger numerical ranges.

Data Transformation – Transformation converts data into a format that can be effectively

processed by AI algorithms. It may involve encoding categorical data (like transaction types or

employee roles) into numerical values, aggregating records into meaningful features, or

restructuring data hierarchies to align with model requirements.

Feature Selection and Engineering – Feature selection identifies the most relevant input variables

(features) that contribute significantly to predicting fraudulent behavior, while discarding

redundant or irrelevant data. Feature engineering, on the other hand, involves creating new

25
variables or combining existing ones to enhance the model’s predictive performance. For

instance, combining transaction frequency and amount can help detect patterns indicative of

money laundering or insider collusion.

Proper preprocessing not only enhances model accuracy but also improves computational

efficiency, reduces overfitting, and strengthens generalization to real-world data. Without these

preparatory steps, even the most sophisticated AI models may yield misleading or inconsistent

results. Inconsistent or biased data can reduce model accuracy and increase false

positives/negatives, undermining fraud detection efforts (Yakubu & Musa, 2023).

2.1.6 Ethical Considerations and Biases in AI Development and Deployment

As Artificial Intelligence (AI) becomes increasingly embedded in financial systems, including

Accounting Information Systems (AIS), the ethical implications of its development and

deployment have come under serious scrutiny. While AI presents vast potential for fraud

detection and operational efficiency, it also introduces significant ethical and legal challenges

that must be addressed to ensure fairness, accountability, transparency, and compliance with data

protection standards.

Algorithmic Bias and Fairness

One of the critical ethical concerns is algorithmic bias. AI systems, particularly those based on

machine learning, are trained on historical data. If the training data reflects existing societal or

institutional biases, the AI model may learn and replicate those biases. This could lead to unfair

treatment or discriminatory outcomes, especially in fraud detection models where certain

customer profiles may be disproportionately flagged due to biased data inputs. For example, if

past fraud cases were more frequently recorded in particular regions or among specific

26
demographic groups, the system might unfairly target those groups in future decisions. Hence,

developers must ensure that AI systems are trained on balanced and representative data to

promote algorithmic fairness (Umar, 2023).

Transparency and Explainability

Another pressing ethical issue is the lack of transparency in AI decision-making, particularly in

deep learning models which function as “black boxes.” These models can produce highly

accurate results but often do so without providing understandable explanations of how the

decisions were reached. This lack of explainability undermines accountability and trust in AI-

based fraud detection systems, especially when financial decisions or accusations of fraud are

made without clear reasoning. Regulatory frameworks and ethical AI standards now emphasize

the need for interpretable AI systems, where users and auditors can trace and understand the

logic behind key decisions.

Data Privacy and Protection

AI systems require vast amounts of data for training and decision-making. In banking

environments, this includes sensitive customer information, financial histories, and transaction

details. The collection, storage, and processing of such data must be done in strict compliance

with data protection laws such as the Nigeria Data Protection Regulation (NDPR) and the

General Data Protection Regulation (GDPR) in the European Union. Any misuse, breach, or

unauthorized access to such data could not only violate customer privacy but also expose the

financial institution to legal liabilities and reputational damage.

Ethical AI Governance and Regulation

To ensure responsible AI deployment, banks and financial institutions must adopt ethical AI

governance frameworks. This includes setting up ethical review boards, ensuring human

27
oversight in AI operations, conducting regular bias audits, and maintaining transparency in AI

system design and usage. Ethical AI practices are necessary not only to foster public trust, but

also to ensure alignment with regulatory expectations and the broader goals of social

responsibility and justice in financial systems.

2.1.7 AI Techniques for Fraud Prevention and Detection

Artificial Intelligence (AI) has revolutionized fraud detection by offering powerful tools and

techniques capable of analyzing vast amounts of data with precision and speed. Commercial

banks increasingly integrate AI into their Accounting Information Systems (AIS) to proactively

detect and prevent fraudulent activities. The following are key AI techniques that enhance fraud

prevention and detection in financial environments:

[Link] Supervised Learning Models for Classification

Supervised learning models represent one of the most widely adopted techniques in fraud

prevention and detection, particularly within the context of accounting information systems.

These models are trained on historical, labeled datasets in which each transaction is pre-

classified as either fraudulent or legitimate. By analyzing such data, the models develop a

predictive framework capable of identifying the likelihood that new or unseen transactions may

be fraudulent. Among the most prominent supervised learning techniques are Decision Trees,

which decompose data into simple decision rules that make classification intuitive and easily

interpretable, making them particularly effective for rule-based fraud detection systems where

clarity is essential. Random Forests, on the other hand, function as ensembles of multiple

decision trees that collectively reduce overfitting and enhance prediction accuracy, thereby

providing more reliable and robust results than a single model. Support Vector Machines

28
(SVMs) are also frequently applied in binary classification tasks, as they perform effectively in

high-dimensional spaces and can uncover complex fraud patterns that simpler linear classifiers

might overlook. Finally, Neural Networks, inspired by the architecture of the human brain, are

capable of identifying highly non-linear and intricate relationships in data, proving especially

valuable when analyzing large and complex datasets common in modern banking operations.

Collectively, these supervised learning techniques enhance the predictive power of artificial

intelligence systems in identifying and preventing fraudulent financial activities within

commercial banks.

Commercial banks employ these models to classify transactions as either fraudulent or non-

fraudulent, improving the accuracy and speed of fraud detection (Ajayi, 2023).

[Link] Unsupervised Learning Models for Anomaly Detection

Unsupervised learning models play a crucial role in fraud detection, particularly in real-world

scenarios where labeled datasets are scarce or unavailable, and where fraudulent behaviors

continuously evolve beyond previously known patterns. Unlike supervised models, which rely

on predefined classifications, unsupervised learning algorithms autonomously identify

underlying structures and detect deviations from normal behavioral trends, making them highly

effective in uncovering previously unseen or emerging fraud schemes. Among the most

commonly employed techniques is K-Means Clustering, which groups transactions based on

their similarity, allowing outliers—potential indicators of fraudulent activity—to be easily

recognized as those that do not fit well within any cluster. Another widely used model, the

Isolation Forest, operates by isolating anomalies instead of profiling normal data points, making

it particularly efficient for detecting rare but high-impact fraudulent transactions. Autoencoders,

a specialized type of neural network, reconstruct input data and measure reconstruction error;

29
transactions with unusually high reconstruction errors are flagged as potential anomalies.

Together, these unsupervised learning approaches enable artificial intelligence systems to adapt

dynamically to new fraud patterns and enhance the overall resilience of accounting information

systems in commercial banking environments.

These models are crucial for identifying fraud patterns that are previously unseen, thus

strengthening fraud detection efforts in dynamic financial environments (Abubakar, 2023).

[Link] Natural Language Processing (NLP) for Analyzing Unstructured Data

Natural Language Processing (NLP) has emerged as a vital branch of artificial intelligence in

modern fraud prevention, as it extends analytical capabilities beyond purely numerical or

transactional data to include unstructured textual information that may contain subtle indicators

of unethical or fraudulent conduct. Unlike conventional data analysis methods that focus on

structured records, NLP empowers accounting information systems to process, interpret, and

derive meaning from vast collections of written communications such as customer complaints,

whistleblower reports, and internal emails, where early warning signs of fraud often reside.

Through techniques such as sentiment analysis, keyword extraction, semantic clustering, and

contextual interpretation, NLP tools can identify suspicious language patterns, detect

inconsistencies in narrative explanations, and flag communications that suggest collusion,

concealment, or manipulation of financial information. By integrating NLP into the fraud

detection process, banks can uncover hidden behavioral cues, strengthen internal surveillance

mechanisms, and achieve a more holistic approach to fraud risk management that combines both

quantitative and qualitative intelligence within the accounting information system framework.

30
By supplementing traditional data models, NLP provides a broader view of fraud risk by

including unstructured text analysis (Musa, 2022).

2.1.8 Integration of Artificial Intelligence within Accounting Information Systems (AIS) for

Fraud Prevention.

The integration of Artificial Intelligence (AI) into Accounting Information Systems (AIS) marks

a pivotal evolution in the field of digital accounting, particularly in enhancing fraud prevention

mechanisms in commercial banking. As financial institutions face increasingly sophisticated

fraudulent schemes, embedding AI into AIS allows for more agile, intelligent, and data-driven

responses to fraud threats. The fusion of AI capabilities with the transactional, reporting, and

audit functionalities of AIS facilitates both preventive and detective fraud controls, ensuring that

modern banking systems are more resilient and responsive to anomalies (Musa et al., 2023).

[Link] Architectural Considerations for Embedding AI Modules in AIS

To effectively implement AI in AIS, the system’s architecture must accommodate intelligent

processing capabilities without disrupting core accounting operations. There are three main

architectural configurations that institutions may consider:

Cloud-based AI Platforms

These platforms offer scalability, flexibility, and reduced costs. Cloud infrastructure allows

banks to leverage advanced AI models and big data processing with minimal internal hardware

requirements. Additionally, cloud solutions enable frequent updates and maintenance of AI tools

to stay ahead of emerging fraud techniques.

On-Premise AI Solutions

31
Some financial institutions, particularly those with heightened data privacy concerns or

regulatory restrictions, opt for on-premise solutions. This setup allows for greater control over

data, better compliance with internal policies, and reduced dependence on third-party vendors.

API and Middleware Integration

Modern AIS often need to interface with legacy systems. Application Programming Interfaces

(APIs) and middleware serve as connectors between AI modules and existing accounting

infrastructures, facilitating seamless data flow and system interoperability.

Most commercial banks adopt a hybrid architecture that blends the flexibility of cloud services

with the control of on-premise deployments. This dual approach ensures operational security

while enabling advanced AI functionalities (Musa et al., 2023).

2.2 Empirical Review.

2.2.1 Empirical Studies on AI Adoption in AIS for Fraud Detection

Several studies have explored the extent of AI adoption in accounting systems for fraud

detection. Alsharari (2021), in a study conducted in Saudi Arabia’s Tabuk region, observed that

while commercial banks were gradually integrating AI tools such as machine learning and expert

systems into their AIS, adoption remained at the early stages due to infrastructural and regulatory

limitations. Similarly, research by Nwaiwu and Eze (2023) in Nigeria revealed that less than

40% of commercial banks had fully adopted AI-enabled fraud detection systems, despite

acknowledging the potential of such technologies to significantly reduce fraud incidences.

In a study involving 150 respondents across five Nigerian commercial banks, Ogunleye and

Abiola (2022) found that most banks relied more on rule-based detection and less on machine

learning or natural language processing tools. This partial adoption was attributed to high costs

32
and lack of skilled personnel. These findings show that while the theoretical benefits of AI in

AIS are acknowledged, practical implementation lags behind due to contextual limitations.

2.2.2 Empirical Studies on Challenges of AI-Based Fraud Prevention Mechanisms

The implementation of AI systems in AIS is often met with operational and structural challeng

es. According to Ugwoke et al. (2022), key challenges include data quality issues, lack of

advanced computational infrastructure, regulatory uncertainty, and staff resistance. Their survey

of bank IT managers in Lagos and Abuja identified model explainability and fear of job

displacement as major barriers to AI acceptance.

Another study by Okafor and Ijeoma (2021) analyzed the challenges of AI deployment across

public and private banks in Nigeria. The study emphasized that inadequate data privacy

frameworks, insufficient training, and high upfront costs were recurring impediments. These

results suggest that beyond technology, sociocultural and economic factors play a critical role in

AI implementation.

2.2.3 Empirical Evidence on the Effectiveness of AI in Fraud Detection and Mitigation

Several empirical studies have established the effectiveness of AI in detecting and mitigating

fraud in banking operations. The work of Ahmed and Al-Yahyaei (2021) demonstrated that AI

systems utilizing supervised learning algorithms like decision trees and random forests achieved

fraud detection accuracy of up to 92% when trained on historical transactional data. Similarly, a

cross-sectional study by Bala and Gimba (2023) in Borno State showed that banks employing

AI-based anomaly detection systems reported a 35% decline in fraud cases over three years.

Moreover, comparative results from the Central Bank of Nigeria’s 2023 fraud report illustrated

that banks using real-time AI alert systems (such as GTBank and Zenith) had lower fraud loss-

33
to-income ratios compared to those still reliant on manual internal control systems. These

findings empirically support the proposition that AI significantly enhances the fraud detection

capabilities of AIS.

2.2.4 Empirical Studies on Regulatory and Operational Factors Influencing AI Integration

Research by Egbunike and Umeoduagu (2020) identified several regulatory barriers affecting AI

deployment in financial systems. Their study emphasized the lack of a specific regulatory

framework for AI-based accounting applications in Nigeria. Furthermore, operational challenges

such as outdated legacy systems and low digital literacy among banking staff hinder seamless AI

integration.

In another empirical survey conducted by Adebayo et al. (2022), respondents from the

compliance departments of Nigerian banks emphasized the role of the Central Bank’s Know-

Your-Customer (KYC) and Anti-Money Laundering (AML) policies in shaping AI deployment

strategies. The study highlighted that AI adoption is more successful when aligned with

regulatory compliance tools, improving both effectiveness and institutional trust.

2.3 Theoretical Framework

A theoretical framework is the foundation upon which a research study is built. It serves to

explain the key concepts and the relationships between them using established theories. This

study focuses on how Artificial Intelligence (AI) can enhance Accounting Information Systems

(AIS) for fraud prevention in commercial banks in Maiduguri, Borno State. Therefore, this

section will explain and connect relevant theories that help understand technology adoption,

fraud behavior, and system effectiveness.

2.3.1 Technology Acceptance Model (TAM)

34
Origin and Background

The Technology Acceptance Model (TAM) was proposed by Fred Davis in 1986, building upon

the Theory of Reasoned Action (TRA) developed by Fishbein and Ajzen. TAM is a widely

accepted theoretical framework used to explain and predict the acceptance and use of technology

by individuals within an organization or system.

Davis (1989) introduced TAM specifically to understand computer usage behavior by examining

the psychological variables that influence users’ decisions about adopting new technologies. The

model identifies two key beliefs that drive technology acceptance:

Perceived Usefulness (PU)

This refers to the degree to which a person believes that using a particular system or technology

would enhance their job performance. If users see the system as beneficial in improving their

efficiency, accuracy, or decision-making, they are more likely to adopt it.

Perceived Ease of Use (PEOU)

This represents the extent to which a person believes that using the system will be free from

effort. In other words, if the system is user-friendly, intuitive, and does not require excessive

technical skills or training, users are more inclined to use it.

TAM posits that both PU and PEOU directly influence the attitude towards using a system,

which in turn affects the behavioral intention to use, ultimately leading to actual system usage.

Application to This Study

The Technology Acceptance Model is particularly relevant to this study on the role of Artificial

Intelligence (AI) in enhancing Accounting Information Systems (AIS) for fraud prevention in

commercial banks in Maiduguri, Borno State.

35
In this context, TAM provides insights into the attitudes and behavioral responses of bank

employees (such as accountants, auditors, IT personnel, and managers) towards the adoption of

AI-powered fraud detection systems. For such AI technologies to be successfully integrated into

existing AIS frameworks, users must perceive them as both useful and easy to use. If bank staff

believe that AI tools can significantly improve the detection and prevention of fraudulent

activities, reduce financial losses, and enhance the overall integrity of financial reporting, their

Perceived Usefulness will be high. Additionally, if these AI applications are designed to be user-

friendly, require minimal training, and integrate seamlessly with current AIS interfaces, their

Perceived Ease of Use will also be high. By understanding and applying the TAM model,

developers and bank management can better design, deploy, and manage AI-driven systems that

are aligned with user expectations and capabilities. This understanding is crucial to overcoming

resistance to technological change and ensuring a smoother transition to AI-enhanced fraud

prevention tools.

Moreover, TAM helps this study establish a theoretical link between human factors (attitudes,

beliefs, and behavior) and technological innovation (AI in AIS). It offers a practical basis for

examining how perceptions influence technology acceptance, which is key to the successful

implementation of AI systems in the banking sector.

In summary, TAM explains the cognitive and psychological drivers behind the acceptance of AI-

based technologies in fraud prevention. It aligns with the study's objectives by providing a

framework for understanding how end-user attitudes influence the success of integrating AI into

AIS in commercial banks. Recognizing and addressing these acceptance factors can enhance

system adoption, improve fraud detection capabilities, and contribute to more secure and

transparent financial operations.

36
2.3.2 Fraud Triangle Theory (FTT)

Origin and Background

The Fraud Triangle Theory was developed by Donald R. Cressey in 1953, a renowned

criminologist who studied the behavioral patterns of incarcerated white-collar criminals.

Through his research, Cressey discovered that individuals who committed occupational fraud

typically did so under the convergence of three critical conditions. These three components form

what is now widely known as the fraud triangle:

Pressure (Incentive)

This refers to the motivation or external/internal force that pushes an individual toward

committing fraud. Common pressures include financial difficulties, unrealistic performance

targets, medical expenses, addiction, or even social status maintenance. The individual may feel

a sense of urgency to resolve their problems through illegitimate means.

Opportunity

This element represents the situation or environment that allows fraud to be perpetrated. It often

arises from weaknesses or loopholes in internal controls, lack of supervision, poor segregation of

duties, or ineffective audit mechanisms. Without a clear opportunity, even motivated individuals

may not act on their intentions.

Rationalization

This is the cognitive process where the fraudster justifies their dishonest actions to themselves.

They may convince themselves that they are only "borrowing" the money, or that their employer

"owes" them, or that no one will be harmed. Rationalization allows individuals to live with their

unethical actions without feeling criminal or guilty. Together, these three elements form a

37
comprehensive psychological and situational model that explains the “why” behind fraudulent

behavior in organizations.

Application to This Study

The Fraud Triangle Theory is directly applicable to this research, which explores the use of

Artificial Intelligence (AI) in strengthening Accounting Information Systems (AIS) to prevent

fraud in commercial banks in Maiduguri, Borno State.

In this context:

Pressure: Employees in banking institutions may experience financial or personal pressures that

could tempt them to commit fraud. While this element is often internal and hidden, certain

behavioral patterns (such as sudden lifestyle changes or high debt levels) can be flagged for risk

assessment.

Opportunity: This is the most actionable component for system-based prevention. Weak or

outdated AIS frameworks may create exploitable gaps, such as unrestricted access to financial

records, inadequate approval hierarchies, or ineffective audit trails. By identifying these

opportunity zones, banks can deploy AI algorithms to tighten controls and automatically monitor

for suspicious behaviors.

Rationalization: Although difficult to measure directly, rationalization can be detected

indirectly through behavior analysis. For instance, if an employee consistently overrides system

checks or works outside of normal hours without justification, AI can flag these as potential

indicators of internal threats.

AI-enhanced AIS can be programmed to monitor all three sides of the triangle. For example:

Machine learning models can detect abnormal transaction patterns that indicate pressure-induced

behavior. Rule-based systems can block or alert on unauthorized access attempts, reducing

38
opportunity. Natural Language Processing (NLP) can even analyze written communication

(emails, reports, etc.) to detect language indicative of rationalization. By applying the fraud

triangle theory, this study underscores how AI tools should not just detect fraud after it occurs

but proactively analyze the behavioral and system-related precursors of fraud. This significantly

strengthens internal controls and serves as a deterrent against unethical financial practices.

The Fraud Triangle Theory provides a behavioral and systemic foundation for understanding and

combating fraud. When applied to AIS, it helps institutions identify critical risk zones and align

AI-driven fraud prevention systems accordingly. Integrating this theory into system design

promotes ethical banking environments, encourages transparency, and reduces the likelihood of

fraud in commercial banks. It also supports the ethical imperative of safeguarding public trust

and institutional accountability in the Nigerian financial sector.

2.3.3 Information Systems Success Model (ISSM)

Origin and Background

The Information Systems Success Model (ISSM) was developed by DeLone and McLean in

1992, with a revised version in 2003. It remains one of the most influential frameworks in

Information Systems (IS) research, offering a multidimensional approach to assessing the

success and effectiveness of information systems within organizations.

DeLone and McLean proposed that system success is not determined by a single factor, but

rather by a set of interrelated components that reflect both technical and organizational

outcomes. These six core dimensions include:

System Quality

39
Refers to the technical performance of the system — including reliability, speed, user interface

design, functionality, and security. A high-quality system should be stable and capable of

performing complex tasks consistently.

Information Quality

Measures the accuracy, relevance, completeness, and timeliness of the information the system

produces. For accounting systems, it’s essential that reports and data outputs reflect real-time and

correct financial activity.

Service Quality

Encompasses the support, maintenance, training, and responsiveness provided to users by the IT

or technical support teams. A system with excellent support services enhances user confidence

and reduces resistance.

Use / Intention to Use

This dimension assesses how often and how effectively the system is used. It can also include

user willingness and motivation to use the system regularly and in accordance with

organizational goals.

User Satisfaction

Indicates the users’ attitudes, comfort, and trust in the system. If users feel the system is helpful,

accessible, and valuable to their job, satisfaction levels will be higher, encouraging continued

use.

Net Benefits

Captures the organizational gains or outcomes resulting from system use, such as efficiency

improvements, cost reductions, decision-making enhancements, and fraud reduction.

40
These components are interconnected, meaning that improved system and information quality

will likely lead to greater use, higher user satisfaction, and ultimately, tangible organizational

benefits.

Application to This Study

The ISSM framework is crucial to this study, which investigates how Artificial Intelligence (AI)

can enhance Accounting Information Systems (AIS) for fraud prevention in commercial banks in

Maiduguri, Borno State. After the implementation of AI-driven systems, evaluating their success

must go beyond just deployment; it should assess how well the systems perform, serve users, and

produce results.

By applying this model, banks can evaluate the real-world effectiveness of their AI investment. It

also serves as a feedback loop for continuous improvement, where shortcomings in system

quality or user satisfaction can be addressed to maximize the system’s fraud prevention

capabilities.

The Information Systems Success Model offers a comprehensive and structured framework for

evaluating the performance, impact, and sustainability of AI-integrated AIS in the banking

sector. Its relevance to this study lies in its ability to bridge technical performance with

organizational outcomes — especially in the area of fraud prevention. In the context of

Maiduguri’s commercial banks, the ISSM helps to assess not just whether AI tools have been

implemented, but whether they are effective, trusted, and beneficial across all levels of the

organization.

41
 CHAPTER THREE

RESEARCH METHODOLOGY

3.1 Study Area

Maiduguri, the capital of Borno State, is located in the North-Eastern region of Nigeria. It lies

between latitude 11°50’N and longitude 13°09’E, situated on the seasonal Ngadda River. The

city shares boundaries with Yobe State to the west and the Republic of Cameroon to the east.

Maiduguri serves as the administrative and economic center of Borno State and plays a strategic

role in financial and commercial activities across the North-East geopolitical zone. As a major

urban center, Maiduguri hosts several branches of Nigeria’s commercial banks, including First

Bank of Nigeria, Zenith Bank, United Bank for Africa (UBA), Access Bank, Fidelity Bank, and

others. These banks offer various financial services ranging from retail banking to digital and

corporate banking solutions. Due to its location and demographic significance, Maiduguri

attracts large volumes of financial transactions from individuals, businesses, and government

institutions. However, the city also faces several operational challenges that affect its financial

42
sector, particularly regarding fraud prevention. Issues such as limited infrastructure, poor internet

access, and regional insecurity have made commercial banks in Maiduguri susceptible to internal

and external fraudulent activities. This makes Maiduguri an appropriate and relevant case study

for examining the role of Artificial Intelligence (AI) in enhancing Accounting Information

Systems (AIS) for fraud prevention in the banking sector.

The selection of Maiduguri as the study area is also influenced by the researcher’s proximity to

the location, ease of access to banking data, and the need to address specific fraud-related issues

that are underexplored in existing literature.

3.2 Population of the Study

The population of the study refers to the entire group of individuals or institutions that are

relevant to the research and from which data may be collected. For this study titled “The Role of

Artificial Intelligence in Enhancing Accounting Information Systems for Fraud Prevention in

Commercial Banks in Maiduguri, Borno State,” the target population comprises employees

working in the commercial banks operating within Maiduguri metropolis. These include staff in

key departments such as internal audit, accounting and finance, information and communication

technology (ICT), risk management, and compliance. The population also includes bank

managers and senior officers who are directly or indirectly involved in fraud prevention and the

use of technology, especially accounting information systems.

As of 2025, there are approximately 15 main commercial banks with active branches in

Maiduguri, including First Bank, UBA, Zenith Bank, Access Bank, Fidelity Bank, EcoBank,

Union Bank, GTBank, Polaris Bank, Stanbic IBTC Bank, TAJ Bank, Wema Bank, Globus Bank,

Unity Bank, and Jaiz Bank. Most of these banks have between 15 to 50 staff per branch

43
depending on their size and scope of operations. Therefore, the estimated total staff population

across all commercial banks in Maiduguri is between 350 to 500 personnel. This study focuses

on this group because they represent the primary stakeholders in implementing and utilizing

accounting information systems and Artificial Intelligence for fraud detection and prevention.

Their insight and experiences will provide critical data for evaluating the extent of AI

integration, challenges in implementation, effectiveness in fraud mitigation, and operational or

regulatory factors influencing system performance within the banking environment in

Maiduguri.

3.3 Sources of Data

The data for this study will be primarily primary data, generated directly from respondents

through the administration of structured questionnaires. The respondents will include selected

employees from various commercial banks operating within Maiduguri, Borno State, especially

those working in departments related to accounting, finance, internal audit, risk management,

and information technology. These data will be obtained through carefully designed research

instruments aimed at gathering information on the adoption, implementation, and effectiveness

of Artificial Intelligence (AI) in enhancing Accounting Information Systems (AIS) for fraud

prevention. The primary data will reflect respondents’ knowledge, experiences, and opinions on

the topic, allowing the researcher to evaluate the practical realities and operational challenges

faced by banks.

Although the focus is on primary data, relevant secondary data may also be used where

necessary. This includes published reports from the Central Bank of Nigeria (CBN), Nigerian

44
Deposit Insurance Corporation (NDIC), journal articles, EFCC records, and previous empirical

studies on AI, AIS, and fraud in the Nigerian banking system. These secondary sources will help

support analysis and interpretation. The combination of primary and relevant secondary data

ensures a robust and reliable basis for addressing the research objectives and drawing informed

conclusions.

3.4 Sample and Sampling Techniques

A sample refers to a subset of the study population selected to represent the entire group in order

to facilitate data collection, analysis, and generalization of findings. In this study, the population

comprises staff of commercial banks operating in Maiduguri, Borno State. However, due to time

and resource constraints, it is not feasible to collect data from every bank employee in the city.

Therefore, a representative sample will be selected from this population using appropriate

sampling techniques.

Sampling Frame

The sampling frame for this study consists of employees from selected commercial banks in

Maiduguri who work in departments relevant to the subject matter of the research — such as

internal control, audit, accounting, IT (Information Technology), risk management, and

compliance. These individuals are considered the most likely to provide meaningful responses

regarding the use of Artificial Intelligence in Accounting Information Systems for fraud

prevention.

To ensure fair representation, the sampling frame is classified as follows:

Bank Name Relevant Departments, Estimated Sample per Bank

Zenith Bank Audit ICT Risk Management 8

45
 Access Bank Accounting Internal Control 8

Operations

UBA Compliance ICT Internal 8

Audit

Fidelity Bank Audit Accounting IT 6

First Bank Internal Control Compliance 8

Risk Unit

Stanbic IBTC Bank Finance IT Audit 6

Union Bank Accounting ICT 6

GTBank Internal Audit Control Risk 6

Total Sample Size: 56 respondents

This sample ensures that various departments involved in fraud monitoring, AIS management,

and technology implementation are coveredp across different commercial banks in Maiduguri.

Sampling Technique

The sampling technique adopted for this study is stratified random sampling. Under this method,

the population was first divided into subgroups (strata) based on departments such as internal

audit, ICT, risk, accounting, and compliance. Afterward, respondents were randomly selected

from each stratum to ensure that every relevant category of staff is adequately represented.

This method is chosen because it minimizes bias and increases the representativeness of the

sample, especially in studies where different professional roles may influence responses.

Stratified sampling also enhances the reliability and validity of findings by ensuring that data is

collected across all critical departments related to fraud prevention and AIS operations.

3.5: Method of Data Collection

46
The primary method of data collection employed in this study is the use of structured

questionnaires. This tool is selected due to its convenience, time efficiency, and suitability for

reaching a relatively large number of respondents within a short period. Given the scope of the

research, which focuses on evaluating the role of Artificial Intelligence in enhancing Accounting

Information Systems for fraud prevention in commercial banks, the questionnaire is designed to

capture both quantitative and qualitative data from bank employees.

The questionnaire is divided into sections that align with the specific objectives of the study.

These sections include items on AI adoption, challenges in implementation, effectiveness of AI

tools, and institutional readiness. Respondents will be required to respond based on their

experiences, knowledge, and professional observations. The instrument will include a mix of

Likert scale items, yes/no questions, and open-ended questions where necessary.

3.6 Method of Data Analysis

The data collected for this study will be analyzed using a combination of descriptive and

inferential statistical tools, depending on the nature of the research questions and hypotheses

tested.

Descriptive Analysis

First, descriptive statistics such as frequencies, percentages, means, and standard deviations will

be used to summarize the respondents’ demographic characteristics and their responses to

questions regarding the adoption of Artificial Intelligence (AI), challenges in implementation,

effectiveness of AI-driven fraud detection, and operational readiness in Maiduguri commercial

banks.

47
This analysis will provide a clear picture of the general trends and patterns in the responses,

helping to establish the prevalence and awareness of AI integration in Accounting Information

Systems (AIS).

Inferential Analysis

To test the research hypotheses and examine relationships between variables, inferential

statistical methods such as the Chi-square test for independence or Pearson correlation may be

applied. These tools will help determine whether observed differences or associations in the data

are statistically significant. All statistical analyses will be conducted using Statistical Package for

the Social Sciences (SPSS) version 25 or Microsoft Excel, depending on the complexity of the

test.

CHAPTER FOUR

DATA PRESENTATION AND ANALYSIS

4.0 Data Presesntation

This chapter presents and analyzes the data collected from the field survey conducted among

staff of commercial banks in Maiduguri, Borno State. Out of 57 questionnaires distributed, all 57

were successfully retrieved, representing a 100% response rate. This high response rate increases

the reliability of the findings and ensures that the opinions expressed are representative of the

population under study. Data presentation involves the systematic arrangement of responses into

tables, charts, and figures for easy interpretation, while data analysis entails the interpretation of

these responses to draw meaningful conclusions. The analysis is presented in sections based on

the structure of the questionnaire: Section A covers demographic information, Section B

48
examines the extent of AI adoption in AIS for fraud detection, Section C evaluates challenges

associated with AI implementation, Section D considers effectiveness of AI in fraud mitigation,

Section E discusses regulatory and operational factors, while Section F captures open-ended

responses.

4.1 Data Analysis

Section A: Demographic Information of Respondents

Table 4.1: Age Distribution of Respondents

Age, No. of respondents, Percentage (%)

18–25, 23, 40.4

26–35, 17, 29.8

36–45, 11, 19.3

46 and above, 6, 10.5

Total, 57, 100

Source: Field Survey, 2025

Interpretation: The majority of respondents (40.4%) are aged between 18–25, followed by

29.8% aged 26–35, while only 10.5% are aged 46 and above. This shows that the banking

workforce in Maiduguri is dominated by young employees, who may be more receptive to AI

technologies.

Table 4.2: Gender Distribution of Respondents

Gender No. of respondents Percentage (%)

Male 49 86.0

Female 8 14.0

Total 57 100

Source: Field Survey, 2025

49
Interpretation: Most respondents are male (86%), reflecting a gender imbalance in the banking

workforce in Borno State.

Table 4.3: Educational Qualification of Respondents

Qualification No. of respondents Percentage (%)

Diploma 0 0.0

Bachelor’s Degree 43 75.4

Master’s Degree 9 15.8

Others 5 8.8

Total 57 100

Source: Field Survey, 2025

Interpretation: Most respondents are degree holders (75.4%), while 15.8% hold a Master’s

degree, showing that the sample consists of well-educated professionals.

Table 4.4: Job Position of Respondents

Job Position No. of respondents Percentage (%)

Teller/Cashier 6 10.5

Accountant 6 10.5

Auditor 3 5.3

IT Officer 11 19.3

Manager 11 19.3

Others 20 35.1

Total 57 100

Source: Field Survey, 2025

50
Interpretation: Respondents are spread across different job roles, with the highest proportion

(35.1%) in “other” categories such as compliance officers and risk managers.

Table 4.5: Working Experience of Respondents

Years of Experience No. of respondent Percentage (%)

Less than 2 years 3 5.3

2–5 years 20 35.1

6–10 years 23 40.4

Above 10 years 11 19.3

Total 57 100

Source: Field Survey, 2025

Interpretation: The majority (40.4%) have 6–10 years of experience, while 35.1% have 2–5

years. This shows that responses are from seasoned professionals.

Section B: Extent of AI Adoption in AIS for Fraud Detection

This section evaluates the extent to which commercial banks in Maiduguri have adopted AI

within their accounting information systems for fraud detection.

Table 4.6: My bank uses AI tools integrated into its AIS for fraud detection.

Response No. of respondents Percentage (%)

Strongly Disagree 14 25.0

Disagree 3 5.0

Neutral 6 10.0

Agree 14 25.0

Strongly Agree 20 35.0

Total 57 100

51
Source: Field Survey, 2025

Interpretation: Most respondents (60%) agree or strongly agree that their banks use AI-

integrated AIS for fraud detection, though a notable 30% disagree. This shows adoption is

underway but not universal.

Table 4.7: AI adoption in our bank’s AIS has increased significantly in recent years.

Response No. of respondents Percentage (%)

Strongly Disagree 6 10.0

Disagree 6 10.0

Neutral 3 5.0

Agree 11 20.0

Strongly Agree 31 55.0

Total 57 100

Source: Field Survey, 2025

Interpretation: The majority (75%) acknowledge recent increases in AI adoption, suggesting

growing recognition of its importance.

Table 4.8: AI-based systems are part of our bank’s daily fraud monitoring processes.

Response No. of respondents Percentage (%)

Strongly Disagree 17 30.0

Disagree 11 20.0

Neutral 11 20.0

Agree 6 10.0

Strongly Agree 12 20.0

Total 57 100

52
Source: Field Survey, 2025

Interpretation: Half of respondents (50%) disagreed, showing that AI daily monitoring is still at

an early stage in many banks.

Table 4.9: The bank invests in upgrading its AIS to incorporate AI technologies.

Response No. of respondests Percentage (%)

Strongly Disagree 0 0.0

Disagree 9 15.0

Neutral 6 10.0

Agree 23 40.0

Strongly Agree 19 35.0

Total 57 100

Source: Field Survey, 2025

Interpretation: Most respondents (75%) confirmed that their banks are actively investing in

upgrading AIS with AI capabilities.

Table 4.10: AI systems in the bank are capable of real-time fraud detection.

Response No. of respondents Percentage (%)

Strongly Disagree 3 5.0

Disagree 2 3.0

Neutral 6 10.0

Agree 23 40.0

Strongly Agree 23 42.0

Total 57 100

Source: Field Survey, 2025

53
Interpretation: An overwhelming 82% agree or strongly agree that AI systems are capable of

real-time fraud detection, confirming its growing role in operational risk management.

Section D: Effectiveness of AI in Detecting and Mitigating Fraudulent Activities

Table 4.16: AI-based systems detect fraud faster than traditional methods.

Response No. of respondents Percentage (%)

Strongly Disagree 2 5.0

Disagree 1 3.0

Neutral 6 10.0

Agree 23 40.0

Strongly Agree 25 42.0

Total 57 100

Source: Field Survey, 2025

Interpretation: A combined 82% of respondents agree that AI detects fraud faster than

traditional methods, confirming AI’s strong value in improving fraud detection speed.

Table 4.17: AI tools help reduce financial losses from fraud.

Response No. of respondents Percentage (%)

Strongly Disagree 3 5.0

Disagree 3 5.0

Neutral 5 10.0

Agree 23 40.0

Strongly Agree 23 40.0

Total 57 100

Source: Field Survey, 2025

54
Interpretation: 80% agree or strongly agree that AI reduces fraud-related financial losses,

indicating that AI contributes significantly to protecting banks’ financial resources.

Table 4.18: The use of AI has improved the accuracy of fraud prevention in the bank.

Response No. of respondents Percentage (%)

Strongly Disagree 0 0.0

Disagree 3 5.0

Neutral 6 10.0

Agree 20 35.0

Strongly Agree 28 50.0

Total 57 100

Source: Field Survey, 2025

Interpretation: A striking 85% believe AI has improved fraud prevention accuracy, making this

one of the strongest positive indicators of AI’s effectiveness.

Table 4.19: AI reduces the number of false positives in fraud detection.

Response No. of respondents Percentage (%)

Strongly Disagree 3 5.0

Disagree 3 5.0

Neutral 8 15.0

Agree 20 35.0

Strongly Agree 23 40.0

Total 57 100

Source: Field Survey, 2025

Interpretation: 75% agree that AI reduces false positives, showing that AI enhances efficiency

by minimizing unnecessary fraud alerts.

55
Table 4.20: Customers have more confidence in the bank’s fraud prevention measures due

to AI.

Response No. of respondents Percentage (%)

Strongly Disagree 2 5.0

Disagree 0 0.0

Neutral 6 10.0

Agree 23 40.0

Strongly Agree 26 45.0

Total 57 100

Source: Field Survey, 2025

Interpretation: An overwhelming 85% agree or strongly agree that customers’ trust improves

due to AI-driven fraud prevention. This highlights AI’s role in boosting customer confidence in

banking systems.

Section E: Regulatory and Operational Factors Influencing AI Integration

Table 4.21: Regulatory guidelines from the CBN support AI adoption for fraud prevention.

Response No. of respondents Percentage (%)

Strongly Disagree 3 5.0

Disagree 6 10.0

Neutral 6 10.0

Agree 20 35.0

Strongly Agree 22 40.0

Total 57 100

Source: Field Survey, 2025

56
Interpretation: 75% of respondents agree that CBN’s regulatory guidelines encourage AI

adoption in fraud prevention, showing that policies are a major driver of AI integration.

Table 4.22: Data privacy laws affect how AI systems are implemented in the bank.

Response No. of respondents Percentage (%)

Strongly Disagree 6 10.0

Disagree 6 10.0

Neutral 6 10.0

Agree 20 35.0

Strongly Agree 19 35.0

Total 57 100

Source: Field Survey, 2025

Interpretation: 70% acknowledge that data privacy laws affect AI implementation, suggesting

banks must balance compliance with technological innovation.

Table 4.23: The bank has clear operational policies for integrating AI into AIS.

Response No. of respondests Percentage (%)

Strongly Disagree 11 20.0

Disagree 17 30.0

Neutral 3 5.0

Agree 14 25.0

Strongly Agree 12 20.0

Total 57 100

Source: Field Survey, 2025

Interpretation: Only 45% agree that banks have clear operational policies for AI integration,

while 50% disagree. This suggests weak institutional frameworks that may slow AI adoption.

57
Table 4.24: Compliance requirements influence the design of AI fraud prevention tools.

Response No. of respondents Percentage (%)

Strongly Disagree 14 25.0

Disagree 11 20.0

Neutral 0 0.0

Agree 20 35.0

Strongly Agree 12 20.0

Total 57 100

Source: Field Survey, 2025

Interpretation: While 55% agree that compliance shapes AI design, a notable 45% disagree,

reflecting mixed perceptions of how much regulatory compliance influences fraud prevention

technologies.

Table 4.25: Regulatory monitoring improves the effectiveness of AI-driven AIS.

Response No. of respondents Percentage (%)

Strongly Disagree 11 20.0

Disagree 17 30.0

Neutral 3 5.0

Agree 14 25.0

Strongly Agree 12 20.0

Total 57 100

Source: Field Survey, 2025

Interpretation: 45% agree that regulatory monitoring improves AI-driven AIS effectiveness,

but 50% disagree, suggesting concerns about overregulation or inefficiencies in enforcement

Section F: Open-Ended Questions

58
Open-ended responses are qualitative, the best approach is to summarize the common themes

raised by respondents.

In your opinion, what more can be done to improve AI-driven fraud prevention in your

bank?

Summary of Responses:

The respondents provided diverse suggestions on strengthening AI-driven fraud prevention in

commercial banks. The major themes are as follows:

1. Capacity Building and Training

Many respondents emphasized the need for continuous staff training to improve the technical

know-how required to operate AI-based fraud prevention tools. Some noted that awareness

programs could reduce resistance to new technologies.

2. Investment in Advanced Technology

Several participants suggested that banks should invest more in advanced AI models with real-

time monitoring, predictive analytics, and anomaly detection. Respondents highlighted the

importance of upgrading existing AIS infrastructure to handle large-scale data efficiently.

3. Stronger Regulatory and Policy Support

Some respondents believed that clearer regulatory frameworks would enable smoother

integration of AI into banking systems. Calls were made for collaboration with the Central Bank

of Nigeria (CBN) to create standardized AI adoption policies.

4. Improved Cybersecurity Measures

Respondents pointed out that AI systems must be complemented with stronger cybersecurity

frameworks to address data breaches and hacking risks.

5. Customer Education and Transparency

59
A few respondents emphasized that customer confidence in AI systems can be improved through

transparency and communication on how fraud detection works.

Please provide any other comments or suggestions.

Summary of Responses:

1. Data Sharing Among Banks – Respondents suggested collaboration and information sharing

across banks to detect cross-institutional fraud more effectively.

2. Cost Reduction Strategies – A number of participants noted that the high cost of AI adoption

must be addressed, possibly through partnerships with fintech companies.

3. Periodic Audits of AI Systems – Respondents recommended that banks periodically evaluate

AI tools to ensure accuracy, fairness, and accountability.

4. Continuous Model Updates – Many respondents stressed the importance of updating AI fraud

detection models regularly to stay ahead of evolving fraud schemes.

5. User-Friendly Systems – Some participants suggested that AI platforms should be simplified

to ensure ease of use by non-technical staff.

Interpretation of Section F

The open-ended responses reveal that while stakeholders recognize the value of AI in fraud

prevention, they believe success largely depends on continuous training, technological upgrades,

regulatory backing, cybersecurity enhancement, and regular system updates. This aligns with

earlier quantitative findings, reinforcing the view that effective AI-driven fraud prevention in

commercial banks requires a combination of technological investment, human resource

development, and strong institutional frameworks.

60
4.2 Testing of Hypotheses

The hypotheses formulated in Chapter Three were tested using the Chi-square (χ²) goodness-of-

fit test because the data for each questionnaire item are categorical (Likert scale: Strongly

Disagree to Strongly Agree). The test compares observed frequencies (O) with expected

frequencies (E) under the null hypothesis (equal distribution across the 5 response categories).

The χ² statistic is:

For this study: total respondents . N=57 With 5 response categories, the expected frequency for

each category under H₀ is:

57
E= =11.40
5

Decision rule (α = 0.05): degrees of freedom . The chi-square critical value is:
2
χ critical ( 4 , 0.05 )=9.488

Reject H₀ when . χ 2 calculated> 9.488

61
4.2.2 Hypothesis One

H₀₁: Artificial intelligence does not significantly enhance the effectiveness of accounting

information systems in commercial banks in Maiduguri, Borno State.

H₁₁: Artificial intelligence significantly enhances the effectiveness of accounting information

systems in commercial banks in Maiduguri, Borno State.

Items used: Q6 – Q10 (Section B: extent of AI adoption / AIS integration).

Below are the item-level χ² calculations. Expected frequency for each category.

Q6 — Percentages: 25% (SD), 5% (D), 10% (N), 25% (A), 35% (SA)

Observed counts (O): 14, 3, 6, 14, 20

Chi-square contributions (rounded to 2 d.p.):

Category O E O−E (O−E)² (O−E)² / E

SD 14 11.40 2.60 6.76 0.59

D 3 11.40 −8.40 70.56 6.19

N 6 11.40 −5.40 29.16 2.56

A 14 11.40 2.60 6.76 0.59

SA 20 11.40 8.60 73.96 6.49

χ²(Q6) 16.42

Q7 — Percentages: 10%, 10%, 5%, 20%, 55%

O: 6, 6, 3, 11, 31

Category O E O−E (O−E)² (O−E)² / E

SD 6 11.40 −5.40 29.16 2.56

D 6 11.40 −5.40 29.16 2.56

62
 N 3 11.40 −8.40 70.56 6.19

A 11 11.40 −0.40 0.16 0.01

SA 31 11.40 19.60 384.16 33.70

χ²(Q7) 45.02

Q8 — Percentages: 30%, 20%, 20%, 10%, 20%

O: 17, 11, 11, 6, 11

Category O E O−E (O−E)² (O−E)² / E

SD 17 11.40 5.60 31.36 2.75

D 11 11.40 −0.40 0.16 0.01

N 11 11.40 −0.40 0.16 0.01

A 6 11.40 −5.40 29.16 2.56

SA 11 11.40 −0.40 0.16 0.01

χ²(Q8) 5.34

Q9 — Percentages: 0%, 15%, 10%, 40%, 35%

O: 0, 9, 6, 23, 20

Category O E O−E (O−E)² (O−E)² / E

SD 0 11.40 −11.40 129.96 11.40

D 9 11.40 −2.40 5.76 0.51

N 6 11.40 −5.40 29.16 2.56

A 23 11.40 11.60 134.56 11.80

63
 SA 20 11.40 8.60 73.96 6.49

χ²(Q9) 32.76

Q10 — Percentages: 5%, 3%, 10%, 40%, 42%

O: 3, 2, 6, 23, 24

Category O E O−E (O−E)² (O−E)² / E

SD 3 11.40 −8.40 70.56 6.19

D 2 11.40 −9.40 88.36 7.75

N 6 11.40 −5.40 29.16 2.56

A 23 11.40 11.60 134.56 11.80

SA 24 11.40 12.60 158.76 13.93

χ²(Q10) 42.23

Total χ ² for Hypothesis One (sum Q6–Q10):

χ ² = 16.42 + 45.02 + 5.34 + 32.76 + 42.23 = 141.77

Decision: Reject
χ ² cal(141.77
H. )> χ ² tab(9.488)→

Interpretation: Respondents’ distribution of answers is significantly different from neutral

(equal distribution), and the skew is toward agreement/strong agreement. Thus there is strong

evidence that AI enhances AIS effectiveness in the sampled banks.

4.2.3 Hypothesis Two

H₀₂: AI-driven accounting information systems do not significantly improve fraud detection and

prevention in commercial banks.

64
H₁₂: AI-driven accounting information systems significantly improve fraud detection and

prevention in commercial banks.

Items used: D1–D5 (Section D: Effectiveness of AI in fraud detection).

D1 — Percentages: 5%, 5%, 15%, 30%, 45%

O: 3, 3, 9, 17, 26

Category O E O−E (O−E)² (O−E)² / E

SD 3 11.40 −8.40 70.56 6.19

D 3 11.40 −8.40 70.56 6.19

N 9 11.40 −2.40 5.76 0.51

A 17 11.40 5.60 31.36 2.75

SA 26 11.40 14.60 213.16 18.70

χ²(D1) 34.34

D2 — Percentages: 10%, 5%, 10%, 40%, 35%

O: 6, 3, 6, 23, 20

Category O E O−E (O−E)² (O−E)² / E

SD 6 11.40 −5.40 29.16 2.56

D 3 11.40 −8.40 70.56 6.19

N 6 11.40 −5.40 29.16 2.56

A 23 11.40 11.60 134.56 11.80

SA 20 11.40 8.60 73.96 6.49

χ²(D2) 29.60

65
D3 — Percentages: 0%, 10%, 15%, 40%, 35%

O: 0,6 9,23,20

Category O E O−E (O−E)² (O−E)² / E

SD 0 11.40 −11.40 129.96 11.40

D 6 11.40 −5.40 29.16 2.56

N 9 11.40 −2.40 5.76 0.51

A 23 11.40 11.60 134.56 11.80

SA 20 11.40 8.60 73.96 6.49

χ²(D3) 32.75

D4 — Percentages: 5%, 10%, 20%, 35%, 30%

O: 3, 6, 11, 20, 17

Category O E O−E (O−E)² (O−E)² / E

SD 3 11.40 −8.40 70.56 6.19

D 6 11.40 −5.40 29.16 2.56

N 11 11.40 −0.40 0.16 0.01

A 20 11.40 8.60 73.96 6.49

SA 17 11.40 5.60 31.36 2.75

χ²(D4) 17.99

D5 — Percentages: 10%, 5%, 15%, 30%, 40%

O: 6, 3, 9, 17, 23

Category O E O−E (O−E)² (O−E)² / E

66
 SD 6 11.40 −5.40 29.16 2.56

D 3 11.40 −8.40 70.56 6.19

N 9 11.40 −2.40 5.76 0.51

A 17 11.40 5.60 31.36 2.75

SA 23 11.40 11.60 134.56 11.80

χ²(D5) 23.81

Total χ ² for Hypothesis Two (sum D1–D5):

χ ² = 34.34 + 29.60 + 32.75 + 17.99 + 23.81 = 138.49

Decision: χReject
² cal(138.49)>
H. χ ² tab(9.488)→

Interpretation: Respondents strongly agree that AI improves fraud detection and prevention;

the distribution is significantly non-neutral.

4.2.4 Hypothesis Three

H₀₃: Artificial intelligence does not significantly contribute to the accuracy and efficiency of

financial reporting in commercial banks.

H₁₃: Artificial intelligence significantly contributes to the accuracy and efficiency of financial

reporting in commercial banks.

Proxy items used: B4, B5 (Section B) and D2, D3, D5 (Section D). These were chosen as the

closest survey items relating to system upgrades, real-time capability, accuracy, loss reduction,

and perceived confidence — all relevant to reporting quality.

We reuse the χ ² contributions already computed:

B4 (same as Q9) χ ² = 32.75

67
B5 (same as Q10) χ² = 42.23

D2 χ ² = 29.60

D3 χ ² = 32.75

D5 χ ² = 23.81

Total χ ² for Hypothesis Three (sum B4,B5,D2,D3,D5):

χ ² = 32.75 + 42.23 + 29.60 + 32.75 + 23.81 = 161.14

Decision: χReject H. )> χ ² tab(9.488)→

Interpretation: The proxy items indicate a strong and significant perception that AI contributes

to accuracy and efficiency in financial reporting.

All three null hypotheses (H₀₁, H₀₂, H₀₃) were rejected at α = 0.05.

The χ ² totals are substantially larger than the critical value 9.488, indicating that respondents’

answers are significantly skewed toward agreement/strong agreement on AI adoption,

effectiveness in fraud detection, and reporting benefits.

These results support the study’s aims: AI adoption is perceived to enhance AIS effectiveness,

improve fraud prevention, and contribute to reporting accuracy/efficiency in commercial banks

in Maiduguri, Borno State.

68
 CHAPTER FIVE

SUMMARY, CONCLUSION AND RECOMMENDATIONS

5.1 Summary

This study examined the role of Artificial Intelligence (AI) in enhancing Accounting Information

Systems (AIS) for fraud prevention in commercial banks operating in Maiduguri, Borno State.

The study was driven by the growing concern over the sophistication of fraudulent activities

within the Nigerian banking system and the increasing adoption of technology-based solutions to

curb such threats. Specifically, the study sought to determine the extent to which AI has been

integrated into accounting information systems, assess its impact on fraud detection and

prevention, and examine the operational and regulatory factors influencing its adoption. The

research was guided by three hypotheses which tested whether artificial intelligence significantly

enhances the effectiveness of AIS, improves fraud detection and prevention, and contributes to

the accuracy and efficiency of financial reporting in commercial banks.

A cross-sectional survey design was employed. Data were collected from 57 respondents drawn

from selected commercial banks in Maiduguri through structured questionnaires. The responses

69
were analyzed using descriptive statistics such as frequencies and percentages, and inferential

statistics through Chi-square tests to validate the hypotheses.

The results revealed that the adoption of AI in AIS among commercial banks in Maiduguri has

considerably improved fraud detection and prevention mechanisms. AI systems have enhanced

the ability of banks to identify anomalies, detect suspicious transactions in real-time, and

strengthen internal control systems. Findings also showed that AI integration in AIS contributes

to more reliable and efficient financial reporting by reducing human errors and promoting data

integrity. However, the study also identified several challenges affecting AI adoption in fraud

prevention, including high implementation costs, inadequate technical expertise, cybersecurity

threats, and management resistance to technological change. Despite these challenges, the overall

findings confirmed that AI plays a significant role in improving fraud prevention and operational

efficiency within the banking sector.

The study was underpinned by the Technology Acceptance Model (TAM), which explains how

perceived usefulness and ease of use influence employees’ acceptance and utilization of AI-

based AIS in banking operations. This theoretical perspective provided insight into the

behavioral and organizational factors that determine the success of AI-driven fraud prevention

systems.

5.2 Conclusion

Based on the findings of this research, it can be concluded that Artificial Intelligence has

emerged as a transformative tool in enhancing Accounting Information Systems for effective

fraud prevention in Nigerian commercial banks. AI technologies, when integrated into AIS,

70
strengthen the capacity of financial institutions to detect, analyze, and prevent fraudulent

transactions with higher precision and speed than traditional systems.

The results further indicate that AI adoption significantly improves the accuracy and reliability

of accounting data, thereby promoting transparency and accountability in financial reporting.

Moreover, AI-based AIS facilitates proactive risk management through predictive analytics,

which enables banks to anticipate and mitigate potential fraud risks before they escalate.

Nevertheless, the study concludes that successful implementation of AI in fraud prevention

depends not only on technological capability but also on human, organizational, and regulatory

factors. Adequate employee training, management support, robust cybersecurity measures, and

compliance with regulatory standards are all critical to sustaining AI’s effectiveness in the

banking environment.

In summary, Artificial Intelligence represents the future of fraud prevention and accounting

systems. When properly implemented and managed, AI-driven AIS can revolutionize fraud

detection and ensure a more resilient, transparent, and accountable financial system in Nigeria’s

banking sector.

5.3 Recommendations

Based on the findings and conclusions of this study, the following recommendations are made:

1. Enhance AI Integration and Infrastructure:

Commercial banks should invest more in advanced AI infrastructure, data analytics tools, and

automation systems that enhance real-time fraud detection within their AIS frameworks.

Continuous technological upgrades should be prioritized to ensure system compatibility and

efficiency.

71
2. Capacity Building and Staff Training:

Regular training programs should be organized for bank staff to build their competence in

operating AI-driven accounting systems. Employees’ awareness of AI tools and their benefits

should be improved to encourage acceptance and reduce resistance to technological change.

3. Strengthen Cybersecurity Frameworks:

Since AI systems rely heavily on data, banks should develop robust cybersecurity policies to

safeguard sensitive financial data from breaches and unauthorized access. Regular audits and

system updates are essential to maintain data integrity and confidentiality.

4. Encourage Regulatory Support:

The Central Bank of Nigeria (CBN) and other regulatory bodies should develop clear guidelines

and frameworks that support and standardize the integration of AI into banking operations.

Regulatory policies should also ensure compliance with data privacy and ethical AI use.

5. Promote Collaborative Research and Innovation:

Banks, academic institutions, and technology developers should collaborate to develop

indigenous AI solutions tailored to the Nigerian banking context. This partnership can reduce

dependence on expensive foreign technologies and enhance the local capacity for innovation.

6. Management Commitment and Change Leadership:

Top management in commercial banks should demonstrate strong commitment to technological

transformation by allocating adequate resources and creating a supportive environment for AI

adoption. Change management strategies should be implemented to align employee attitudes

with organizational goals.

72
7. Continuous Evaluation of AI Systems:

Banks should periodically review and evaluate the performance of their AI-driven AIS to ensure

that they remain effective and aligned with emerging fraud patterns and regulatory requirements.

Continuous improvement will ensure the long-term sustainability of AI adoption in the sector.

73