Unit:1 BI

Q.1 Explain the concepts of Data, Information, and Knowledge in the context of Business
Intelligence.

1. Data :-

Data is the raw and unprocessed facts or figures collected from different sources. It has
no meaning by itself until it is organized or analyzed.

Examples:

⚫ Sales numbers: 500, 650, 720

⚫ Customer names
⚫ Product IDs
⚫ Transaction dates

Example in Business:
A store records daily sales like:
500, 650, 720 units sold.

These numbers alone are just raw data.

2. Information

Information is processed and organized data that gives meaning and helps in
understanding a situation.

Example:
If the sales data is organized into a report:

Day Units Sold

Monday 500
Tuesday 650
Wednesday 720

Now we can see that sales are increasing every day.

This organized data becomes information.

3. Knowledge

Knowledge is the understanding or insight gained from information that helps in making
decisions.
 Example:
From the sales information, a manager may understand:

◼ Sales increase during weekdays.

◼ More stock should be kept on busy days.

This understanding helps in better business decisions.

Q.2 Analyze a business scenario and identify how Business Intelligence tasks can be
employed for strategic decision-making.

 Business Scenario

Suppose a retail company sells products both online and in physical stores. Recently, the
company noticed that overall sales are decreasing, but they do not know the exact reason.

To understand the problem and make better decisions, the company uses Business
Intelligence (BI).

 Use of Business Intelligence Tasks

1. Data Collection

The company collects data from different sources such as:

⚫ Sales transactions
⚫ Customer purchase history
⚫ Online website traffic
⚫ Inventory records

Example: Daily sales data, product categories, customer locations, and payment details.

2. Data Integration and Storage

All collected data is stored in a data warehouse where information from different systems is
combined and organized.

Purpose:
To keep all business data in one place for easy analysis.

3. Data Analysis

Using BI tools, the company analyzes the data to identify patterns and trends.

Example findings:

• Sales are high on weekends.

• Certain products sell more in specific regions.
 • Online sales are increasing but store sales are decreasing.

4. Data Visualization

BI tools create dashboards, charts, and reports to help managers easily understand the
data.

Example:

• Sales trend graphs

• Regional sales comparison
• Product performance charts

5. Strategic Decision-Making

Based on the analysis, the company can make important business decisions such as:

• Increasing online marketing campaigns

• Restocking popular products
• Offering discounts in low-performing regions
• Improving store promotions

Q.3 Evaluate the goals of Business Intelligence and its future trends.

 Goals of Business Intelligence (BI)

Business Intelligence helps organizations collect, analyze, and use data to make better
business decisions. The main goals are:

1. Better Decision Making

BI helps managers make accurate and quick decisions based on data instead of guesswork.

2. Improve Business Performance

By analyzing sales, customers, and operations, companies can increase profit and efficiency.

3. Identify Trends and Patterns

BI tools analyze historical data to find patterns, such as customer buying behavior or
seasonal sales trends.

4. Increase Competitive Advantage

Organizations can understand the market and competitors better, helping them stay ahead in
business.
5. Improve Customer Satisfaction

BI helps analyze customer preferences and feedback, allowing businesses to provide better
products and services.

 Future Trends of Business Intelligence

1. Artificial Intelligence Integration

BI will increasingly use AI and Machine Learning to automatically analyze data and predict future trends.

2. Real-Time Data Analysis

Businesses will use BI tools to analyze data instantly, helping them make faster decisions.

3. Self-Service BI

Employees without technical knowledge will be able to analyze data using simple dashboards and tools.

4. Cloud-Based BI

More companies will store and analyze data on cloud platforms, making BI tools easier to access.

5. Mobile BI

Business data and reports will be available on mobile devices, allowing managers to check insights anytime.

Q [Link] the connection between Business Intelligence and Decision Support System.

Connection between Business Intelligence (BI) and Decision Support System (DSS)

Business Intelligence (BI) and Decision Support System (DSS) are technologies that help
organizations analyze data and make better business decisions. BI provides the data analysis
and insights, while DSS uses this information to support decision-making.

1. Business Intelligence (BI)

Business Intelligence is a system that collects, stores, and analyzes business data from
different sources.
It uses tools such as reports, dashboards, and data visualization to convert raw data into
useful information.

Example:
A company analyzes sales data to identify which product sells the most.
2. Decision Support System (DSS)

A Decision Support System is a computer-based system that helps managers make decisions
by analyzing data and suggesting possible solutions.

It uses models, analytical tools, and reports to support business decisions.

Example:
A manager uses DSS to decide how much stock to order for the next month.

3. Connection Between BI and DSS

Business Intelligence and DSS are closely related because BI provides the information that
DSS uses for decision-making.

⚫ BI collects and analyzes data.

⚫ DSS uses this analyzed data to help managers choose the best decision.

For example:
BI shows that sales increase during festival seasons, and DSS helps managers decide to
increase product inventory during that period.

Q [Link] a Business Intelligence architecture suitable for a specific industry and justify
your choices.
Business Intelligence (BI) Architecture for the Retail Industry

In the retail industry, companies need to analyze sales, customer behavior, and inventory to
make better business decisions. A Business Intelligence architecture helps collect, process,
and analyze this data.

1. Data Sources

This is the first layer where data is collected from different systems.

Examples:

⚫ Sales transactions from stores

⚫ Online shopping data
⚫ Customer information
⚫ Inventory records
⚫ Supplier data

Justification:
Retail businesses generate data from many places, so collecting all this data helps understand
overall business performance.

2. ETL Process (Extract, Transform, Load)

The ETL process is used to:

⚫ Extract data from different sources

⚫ Transform it by cleaning and organizing the data
⚫ Load it into a central storage system

Justification:
This step ensures that the data is accurate, consistent, and ready for analysis.

3. Data Warehouse

A data warehouse stores all processed business data in one central location.

Justification:
It allows companies to store large amounts of historical data and analyze it easily.
4. Data Analysis Tools

BI tools are used to analyze the stored data.

Examples:

⚫ Data mining
⚫ Query tools
⚫ OLAP analysis

Justification:
These tools help find patterns, trends, and insights in sales, customers, and product
performance.

5. Reporting and Visualization

The analyzed data is presented using:

⚫ Dashboards
⚫ Charts
⚫ Reports

Justification:
Visual reports help managers quickly understand business performance and make
decisions.

6. Decision-Making Layer

Managers use the insights to make strategic decisions, such as:

⚫ Increasing stock of popular products

⚫ Offering discounts on slow-selling items
⚫ Planning marketing strategies

Justification:
This helps improve sales, customer satisfaction, and profitability.
Q.6 Assess the impact of Business Intelligence on improving decision-making processes in
organizations.

Impact of Business Intelligence (BI) on Improving Decision-Making in Organizations

Business Intelligence (BI) helps organizations collect, analyze, and present data so that
managers can make better and faster decisions. It converts raw data into meaningful
insights that support business strategies.

1. Data-Driven Decision Making

BI allows organizations to make decisions based on actual data instead of assumptions.

Example:
A company analyzes sales reports to decide which products should be promoted.

2. Faster Decision-Making

BI tools provide real-time reports and dashboards, helping managers quickly understand
business performance.

Example:
Managers can instantly see daily sales and take action if sales decrease.

3. Identifying Trends and Patterns

BI analyzes historical data to find trends and patterns in customer behavior, sales, and
market demand.

Example:
A retail company can identify that sales increase during festival seasons.

4. Improved Business Efficiency

By analyzing operational data, organizations can reduce costs and improve productivity.

Example:
BI helps companies manage inventory efficiently and avoid overstocking.
5. Better Strategic Planning

BI provides insights that help organizations plan future strategies and business growth.

Example:
Companies can decide where to open new stores based on sales and customer data.

Remaining points:

1. Definition of Business Intelligence

Business Intelligence (BI) is the process of collecting and analyzing business data to
convert it into useful information. It helps organizations make better decisions and
improve business performance.

2. Brief History of Business Intelligence (BI):

• The term Business Intelligence was first introduced by Hans Peter Luhn in 1958.
• In the 1960s–1970s, organizations used Decision Support Systems (DSS) for data
analysis.
• In the 1980s–1990s, technologies like data warehouses and reporting tools were
developed.
• In the 2000s, BI became more advanced with data mining, dashboards, and
visualization tools.
• Today, BI uses Big Data, AI, and Machine Learning to support better business
decisions.

3. Architecture & Components of Business Intelligence

BI Architecture means the structure that shows how data is collected, stored, analyzed,
and presented in a BI system.
Main Components:

• Data Sources: Databases, files, websites, etc. where data is collected.

• ETL (Extract, Transform, Load): Process that collects, cleans, and loads data into
storage.
• Data Warehouse: Central place to store large amounts of organized data.
• Data Analysis Tools: Tools used to analyze the stored data.
• Reporting & Dashboards: Display results using reports, charts, and graphs for
decision making.
•

4. Business Intelligence Scenarios

BI scenarios are real-life situations where BI tools are used to analyze business data and
support decision making.

Examples:

• Sales analysis to increase profit

• Customer behavior analysis
• Market trend analysis
• Inventory management

BI helps organizations make better business decisions using data.

[Link] Formats (Business Intelligence)

Analysis formats are the ways in which analyzed data is presented to users so that they
can easily understand business insights and make decisions.

1. Reports
Reports present data in a structured and detailed form. They usually contain tables,
summaries, and explanations of business data such as sales reports or performance reports.

2. Dashboards
Dashboards show important business information on a single screen using visual
elements. They help managers quickly see key performance indicators (KPIs) and business
status.

3. Charts and Graphs

Charts and graphs are visual representations of data such as bar charts, pie charts, and line
graphs. They make it easier to compare values and understand trends.
4. Data Visualization Tools
These tools convert complex data into visual formats like maps, charts, and interactive
dashboards. They help users analyze large data easily and understand patterns quickly.

In short:
Analysis formats help users clearly understand business data and insights for better
decision making.

[Link] trends of BI

• Artificial Intelligence (AI) – BI will use AI to automatically analyze data and predict
future trends.

• Big Data Analysis – BI will analyze very large volumes of data from different sources.

• Real-time Data Analysis – Businesses will get insights instantly to make quick decisions.

• Better Data Visualization Tools – Advanced dashboards, charts, and interactive

visualizations will make data easier to understand.

7. Simon’s Decision Making Process

Herbert Simon proposed a four-stage model for decision making. It explains how
managers identify problems and choose the best solution.

1. Intelligence Stage
In this stage, the problem is identified and clearly understood. Data is collected and
analyzed to find the reason for the problem.

2. Design Stage
In this stage, different possible solutions (alternatives) are developed to solve the problem.
These alternatives are studied and compared.
3. Choice Stage
In this stage, the decision maker evaluates all alternatives and selects the best solution.

4. Implementation Stage
In this stage, the selected solution is implemented in the organization and its results are
monitored to check whether the problem is solved.

In short:
Simon’s model helps in identifying problems, finding solutions, selecting the best option,
and implementing it.

8. Definition of Decision Support System (DSS)

A Decision Support System (DSS) is a computer-based system that helps managers and
organizations make better decisions by analyzing data and providing useful information.

9. Information Systems Support for Decision Making

Information systems help in decision making by collecting, processing, storing, and
analyzing data.
They provide accurate and timely information which helps managers take better decisions.
UNIT 2:-BI
Q1 Explain how Logical Structures, such as ontology and frame, are used in BI modeling.

Use of Logical Structures in Business Intelligence (BI) Modeling

In Business Intelligence (BI), logical structures help organize and represent business
knowledge in a structured way. They make it easier to analyze data and support decision-
making. Two common logical structures used in BI modeling are Ontology and Frame.

1. Ontology

Ontology is a structured representation of concepts, relationships, and rules within a specific

domain.

It defines:

⚫ Entities (objects)
⚫ Relationships between them
⚫ Rules or properties

Example in Business:
In a retail BI system:

• Customer buys Product

• Product belongs to a Category

This structure helps BI systems understand how different business elements are related.

Importance in BI:

• Improves data organization

• Helps in knowledge sharing
• Supports better data analysis

2. Frame

A Frame is a structure used to represent knowledge about a specific object or situation using
attributes and values.

A frame contains:

• Slots (attributes)
• Values (data for those attributes)

Example:

Frame: Product
Slot (Attribute) Value
Product Name Laptop
Price 50,000
Category Electronics
Stock 100

Importance in BI:

• Organizes business data clearly

• Helps represent detailed information about objects
• Supports knowledge-based analysis

Q.2 Identify the key components of Model Building in BI.

Key Components of Model Building in Business Intelligence (BI)

Model Building in Business Intelligence is the process of creating models to analyze data
and predict future outcomes. These models help organizations make better business
decisions.

The key components of model building in BI are:

1. Data Collection

The first step is to collect data from different sources such as:

• Databases
• Transaction systems
• Customer records
• Sales data

Purpose:
To gather relevant data needed for analysis.

2. Data Preparation

In this step, the collected data is cleaned and organized.

It includes:

• Removing errors or duplicates

• Handling missing values
• Formatting the data
Purpose:
To ensure the data is accurate and ready for modeling.

3. Model Selection

The appropriate analytical or statistical model is selected based on the problem.

Examples:

• Regression models
• Classification models
• Clustering models

Purpose:
To choose the best method for analyzing the data.

4. Model Training

The selected model is applied to the prepared data to identify patterns and relationships.

Purpose:
To allow the model to learn from historical data.

5. Model Evaluation

The performance of the model is tested to check accuracy and reliability.

Purpose:
To ensure the model provides correct predictions or insights.

6. Model Deployment

The final model is implemented in the BI system to support real business decisions.

Purpose:
To use the model for forecasting, analysis, and decision-making.
Q.3 Utilize Business Process Model and Notation (BPMN) to model a complete business
process in a given case study.

Using Business Process Model and Notation (BPMN) to Model a Business Process

Business Process Model and Notation (BPMN) is a graphical method used to represent
business processes in a clear and standardized way. It helps organizations understand,
analyze, and improve their business operations.

BPMN mainly uses the following elements:

• Events – Start or end of a process

• Activities/Tasks – Work performed in the process
• Gateways – Decision points
• Flow lines – Show the sequence of steps

Case Study: Online Order Processing System

A company sells products through an online store. The process from placing an order to
delivering the product can be modeled using BPMN.

BPMN Process Steps

1. Start Event
The process begins when a customer places an order on the website.
2. Task: Receive Order
The system receives and records the order details.
3. Task: Check Product Availability
The system checks whether the product is available in stock.
4. Gateway (Decision Point)

⚫ If the product is available, the process continues.

⚫ If the product is not available, the order is cancelled and the customer is notified.

5. Task: Process Payment

The system verifies and processes the customer's payment.
6. Task: Pack the Product
The warehouse team prepares and packs the ordered product.
 7. Task: Ship the Product
The product is shipped to the customer through a delivery service.
8. End Event
The process ends when the customer receives the product.

Simple BPMN Flow (Text Representation)

Start Event → Receive Order → Check Product Availability →

Gateway (Available?) →
Yes → Process Payment → Pack Product → Ship Product → End Event
No → Cancel Order → Notify Customer → End Event

• Models used in Business Intelligence

1. Descriptive Models
Used to analyze past data and understand what happened in the business.
Example: Sales reports, dashboards.
2. Predictive Models
Used to predict future outcomes using historical data.
Example: Sales forecasting, customer churn prediction.
3. Prescriptive Models
Suggest the best decision or action based on analysis.
Example: Product recommendation systems.
4. Statistical Models
Use mathematical and statistical methods to analyze data.
Example: Regression analysis.
5. Data Mining Models
Used to discover patterns and hidden relationships in large datasets.
Example: Market basket analysis.
 • Modelling
Modelling is the process of creating and developing models using data and techniques to
analyze business problems and make better decisions.

Steps in Modelling:

1. Identify the business problem

2. Collect and prepare data
3. Choose modelling technique
4. Build the model
5. Test and evaluate the model

Example:
Creating a model to predict which customers are likely to buy a product.

• Model Presentation
Model Presentation means how the results of a model are shown to users so that they can
easily understand the information and make decisions.

After building and analyzing a model, the results must be presented in a clear and simple
format.

➢ Common formats of model presentation:

1. Charts and Graphs – Visual representation of data such as bar charts, pie charts, and
line graphs. They help users quickly see patterns and comparisons.
2. Dashboards – A dashboard displays important business information in one place
using charts, numbers, and indicators. It provides a quick overview of business
performance.
3. Reports – Reports present detailed information and analysis about business data in
written form. They are often used for business review and planning.
4. Data Visualization Tools – Tools that convert complex data into visual forms such as
diagrams and interactive charts to make data easier to understand.

• Model Assessment and Quality of Models

Model Assessment means evaluating or checking how well a model works after it is
built. It helps to determine whether the model is giving correct and useful results for
decision making.

In Business Intelligence, it is important to check the quality of the model before using it in
real business situations.
Important factors for model quality:

1. Accuracy – The model should give correct predictions and results.

2. Reliability – The model should work consistently every time it is used.
3. Efficiency – The model should process data quickly and use resources properly.
4. Simplicity – The model should be easy to understand and use.

• Modelling using Graph Structure

Graph structure represents data using:

• Nodes (vertices) → objects

• Edges (links) → relationships

Example:

• Customer node connected to Product node.

Graph models help analyze:

• Social networks
• Customer relationships
• Recommendation systems

• Modelling using Probabilistic Structures

Probabilistic modelling is used when there is uncertainty in data or outcomes. It uses
probability theory to represent and analyze uncertain situations.

These models calculate the likelihood (chance) of different outcomes based on available
data. They help businesses make better decisions even when the information is incomplete or
uncertain.

Common probabilistic techniques:

1. Bayesian Networks – A graphical model that shows relationships between variables

using probability. It helps in predicting outcomes based on conditions.
2. Markov Models – A model that predicts the next state of a system based on the
current state using probability.

Example:
A company can use probabilistic models to predict whether a customer is likely to buy a
product based on past purchasing behavior.
 • Modelling using Analytical Structure
Analytical modelling uses mathematics and statistical techniques to analyze business
data and support decision making.

These models help businesses in:

• Forecasting future trends

• Optimization of resources and processes
• Decision analysis for better business strategies

Examples:

• Regression analysis – Finds relationships between variables.

• Time series analysis – Analyzes data over time to predict future trends.

Conclusion:
Analytical models are widely used in business forecasting, planning, and performance
analysis.

• Data Generation
Data Generation means the process of creating or collecting data from different sources
for analysis. In Business Intelligence, data is generated from many activities that happen in
an organization.

This data is later used for analysis, reporting, and building models to support decision
making.

Common sources of data generation:

• Transactions – Sales records, purchase details, billing information.

• Sensors – Devices that collect data automatically (temperature, machines, etc.).
• Surveys – Data collected from customer feedback and questionnaires.
• Social Media – Data from platforms like comments, likes, and reviews.
• Business Operations – Daily activities such as inventory management and customer
records.
 • 11. Role of Time

Time is very important in BI because business data changes over time.

Examples:

• Daily sales
• Monthly revenue
• Yearly growth

Time helps analyze:

• Trends
• Patterns
• Forecast future performance

Example:
Sales increasing during festival seasons.

• 12. Data Quality

Data Quality refers to the accuracy, reliability, and usefulness of data used in Business
Intelligence. High-quality data is important because business decisions depend on correct
and complete information.

Good data quality should have the following characteristics:

• Accuracy – Data should be correct and free from errors.

• Completeness – All required data should be available and not missing.
• Consistency – Data should be the same across different systems and databases.
• Timeliness – Data should be updated and available at the right time.

If the data quality is poor, it can lead to incorrect analysis and wrong business decisions.

Example:
If customer data contains wrong addresses or phone numbers, the company may make
ineffective marketing decisions.