0% found this document useful (0 votes)
11 views16 pages

AI Student Performance Evaluation System

The document outlines a project report for an AI-Based Academic Evaluation System aimed at automating student performance analysis in educational institutions. It highlights the inefficiencies of manual evaluation methods and presents a solution that utilizes Python, Streamlit, and other tools to provide accurate, timely, and visual performance assessments. The system categorizes students based on their performance scores and supports data-driven decision-making for faculty and administrators.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
11 views16 pages

AI Student Performance Evaluation System

The document outlines a project report for an AI-Based Academic Evaluation System aimed at automating student performance analysis in educational institutions. It highlights the inefficiencies of manual evaluation methods and presents a solution that utilizes Python, Streamlit, and other tools to provide accurate, timely, and visual performance assessments. The system categorizes students based on their performance scores and supports data-driven decision-making for faculty and administrators.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

STUDENT PERFORMANCE ANALYSIS

AI-Based Academic Evaluation System

A Minor Project -- I Report Submitted to

Department of Computer Science and Engineering


Bansal Institute of Research & Technology
BHOPAL (M. P.)

2023 - 2027

Submitted By

Jatindra Patel (0173CS231071)


Abhinav Raghuwanshi (0173CS231004)
Aditya Paswan (0173CS231009)

Under The Guidance of

Prof. Neha Pawar


(Assistant Professor, Dept. of CSE)

Bansal Institute of Research & Technology


BHOPAL (M. P.)

( Affiliated to Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal )


(Session 2023 - 2027)

Department of Computer Science and Engineering

CERTIFICATE

This is to certify that Jatindra Patel, Abhinav Raghuwanshi, Aditya


Paswan students of Vth semester in Bansal Institute of Research and
Technology have completed their Minor Project I on “Student
Performance Analysis – AI Based Academic Evaluation System”, as per
the syllabus and has submitted a satisfactory report on this project as a
partial fulfillment towards the award of degree of Bachelor of Technology
in Computer Science and Engineering under Rajiv Gandhi Proudyogiki
Vishwavidyalaya, Bhopal.

Prof. Santosh Mishra Prof. Neha Pawar

H.O.D., CSE Dept. Project Guide


ACKNOWLEDGEMENT

We express our sincere gratitude to Prof. Neha Pawar, Project Guide, for
her continuous guidance, motivation, and valuable suggestions
throughout the development of this project. We are also thankful to Prof.
Santosh Kumar Mishra, H.O.D., CSE Department, for providing us the
opportunity and resources to complete this project successfully.
Finally, we thank our friends and family members for their constant
support.
TABLE OF CONTENT`S

Chapter Topic
1 Introduction
2 Literature Survey
3 Analysis
4 Design
5 Implementation and Testing
6 Conclusion
A References
B Glossary
C FUTURE ENHANCEMENTS

D User Manual
CHAPTER 1 – INTRODUCTION

1.1 Overview and Issues Involved

In the modern education system, academic institutions generate a large amount of


student-related data such as internal assessment marks, unit test results, attendance
records, and assignment scores. Traditionally, this data is analyzed manually by
teachers or academic staff, which requires significant time and effort. Manual
analysis often involves maintaining registers, spreadsheets, and handwritten
records, making the process inefficient and difficult to manage as the number of
students increases.
One of the major issues with manual performance analysis is the high possibility of
human errors. Mistakes in data entry, calculation errors, and misinterpretation of
results can lead to inaccurate performance evaluation. Due to these errors,
deserving students may not be identified correctly, and weak students may not
receive timely academic support.
Furthermore, there is no centralized system in many institutions where all
academic data can be stored, analyzed, and visualized at one place. The absence of
a centralized performance monitoring system makes it difficult for faculty, HODs,
and administrators to gain an overall view of class performance, subject difficulty,
and academic trends.

1.2 Problem Statement

Despite the availability of digital tools, many educational institutions still rely on
traditional manual methods for analyzing student performance.
 Manual performance analysis is time-consuming and requires continuous
human involvement.
 The process is prone to calculation and data entry errors, affecting result
accuracy.
 Faculty members find it difficult to identify weak and average students at an
early stage.
 There is no centralized platform to monitor subject-wise and overall student
performance.
 Lack of graphical and visual representation of academic data reduces
analytical clarity.
1.3 Objectives

The main objectives of the proposed Student Performance Analysis System are as
follows:
 To develop an automated system that analyzes student academic
performance efficiently.
 To reduce manual effort and eliminate human errors in performance
evaluation.
 To classify students into different performance categories such as A, B, C,
and D based on calculated scores.
 To provide subject-wise as well as overall class performance analysis.
 To assist faculty members in identifying weak students at an early stage.
 To support data-driven academic decisions through graphical visualization
and reports.
These objectives aim to improve the overall academic monitoring process and
enhance student performance outcomes.

1.4 Proposed Solution

The proposed system is an AI-based Student Performance Analysis System


designed to automate the evaluation of student academic performance. The system
accepts structured academic data such as internal assessment marks, unit test
scores, assignment marks, and attendance percentage as input.
Using predefined weightage logic, the system calculates an overall performance
score for each student. Based on this score, students are automatically classified
into performance categories such as A, B, C, and D. This classification helps
faculty members quickly identify top-performing, average, and weak students.
The system also provides graphical and visual insights using charts and plots,
making the analysis more intuitive and easy to understand. Unlike traditional
manual systems, the proposed solution is faster, more accurate, and scalable. It
enables real-time analysis and centralized monitoring of academic performance,
thereby improving efficiency and decision-making in educational institutions.
CHAPTER 2 – LITERATURE SURVEY

2.1 Methodology
The methodology of the proposed system is based on a data-driven approach for
analyzing student academic performance. In traditional systems, performance
evaluation is usually done manually, which involves maintaining records,
calculating scores, and analyzing results by human effort. Such methods are time-
consuming, less efficient, and prone to errors.

In the proposed system, structured academic data such as student enrollment


number, name, subject details, internal assessment marks, unit test marks,
assignment marks, and attendance percentage are collected in digital format. This
data is then processed using predefined rules and weighted performance
calculation logic.

Each assessment component is assigned a specific weightage to ensure fair


evaluation of student performance. The system calculates an overall performance
score by combining these weighted values. Based on the final score, students are
categorized into different performance levels such as A, B, C, and D.

The methodology emphasizes automation, accuracy, and consistency in


performance evaluation. By using computational techniques and data analysis
libraries, the system reduces manual effort and ensures reliable and repeatable
results. The use of graphical visualization further helps faculty members to
understand performance trends and patterns easily.

2.2 Technologies and Tools Used


The successful implementation of the Student Performance Analysis System requires
the use of reliable and efficient technologies.

Python
Python is a high-level programming language known for its simplicity and
readability. It is widely used for data analysis and application development. In this
project, Python is used to implement the performance calculation logic and data
processing functionalities.
Streamlit
Streamlit is an open-source Python framework used to build interactive and user-
friendly web applications. It allows developers to create data-driven applications
with minimal coding effort. Streamlit is used in this project to design the web-
based interface where users can upload student data files and view analysis results.
Its real-time interaction capability makes the system responsive and easy to use for
faculty members.

Pandas
Pandas is a powerful Python library used for data manipulation and analysis. It
provides efficient data structures such as DataFrames that make handling large
datasets simple and fast. In this project, Pandas is used to read CSV and Excel
files, clean and preprocess academic data, and perform calculations on student
records. It plays a crucial role in managing structured student data accurately.

Plotly
Plotly is a data visualization library that enables the creation of interactive and
visually appealing charts and graphs. It helps in presenting complex data in an
easily understandable format. In this project, Plotly is used to generate
performance graphs, subject-wise analysis charts, and overall class performance
visualizations. These visual representations help faculty and administrators to
make informed academic decisions.

Other Supporting Tools


Apart from the main technologies, standard development tools such as code editors
and web browsers are used for testing and debugging the application. CSV and
Excel files are used as input data sources, making the system flexible and easy to
integrate with existing academic records.
Chapter 3 – Analysis

3.1 Software Requirements


The software requirements define the necessary software environment needed for
the successful execution of the proposed Student Performance Analysis System.

Operating System:
Windows 7 or above is used as the operating system because it is stable, user-
friendly, and supports all the required development tools and libraries.

Programming Language:
Python is used as the core programming language due to its simplicity, readability,
and strong support for data analysis and visualization libraries.

Libraries and Frameworks:

 Streamlit: Used to develop the interactive web-based interface of the


system.

 Pandas: Used for reading, processing, and analyzing student academic data
from CSV and Excel files.

 Plotly: Used to generate interactive graphs and visualizations for


performance analysis.

These software tools together ensure efficient data processing, accurate analysis,
and clear visualization of results.

3.2 Hardware Requirements


The hardware requirements specify the minimum system configuration required to
run the application smoothly.

Processor:
An Intel Core i3 processor or above is recommended to ensure faster data
processing and smooth execution of the application.
RAM:
A minimum of 4 GB RAM is required to handle academic datasets efficiently and
support multitasking during analysis.

Storage:
At least 100 GB of storage is required for storing project files, datasets, and
generated reports.

3.3 Use Case Model


The Use Case Model represents the interaction between users and the system.
The primary users of the system are faculty members and Heads of Departments
(HODs).

Faculty members upload student academic data in CSV or Excel format and analyze
individual as well as subject-wise performance. HODs can use the system to
monitor overall class performance, identify trends, and make academic decisions.

The system processes the uploaded data, performs calculations, categorizes students,
and displays the results in graphical and tabular form. This model helps in
understanding the functional flow of the system.

3.4 Use Case Description


The major use cases of the Student Performance Analysis System are described
below:

Upload Student Data:


The user uploads student academic data files containing marks and attendance
details.
Analyze Performance:
The system processes the uploaded data and calculates the overall performance
score using predefined logic.

Categorize Students:
Based on calculated scores, students are categorized into performance levels such
as A, B, C, and D.

Generate Reports:
The system generates subject-wise and overall performance reports for better
evaluation.

Visualize Results:
Performance results are displayed using charts and graphs, enabling easy
understanding and comparison.
CHAPTER 4 – DESIGN

4.1 Technology Selection


Python is chosen due to its simplicity, strong data analysis libraries, and easy
integration with web frameworks like Streamlit.

Python provides a wide range of libraries that are specifically designed for
handling and analyzing structured data. Its easy syntax reduces development
time and makes the code easy to understand and maintain. Additionally,
Python integrates seamlessly with modern web frameworks.

4.2 System Flow Design


The system follows a simple flow:

1. Upload CSV file

2. Process data

3. Calculate performance score

4. Categorize students

5. Display visual results

4.3 Database Design

In the current version of the system, CSV and Excel files are used as the
primary data source for storing and processing student academic
information. This file-based approach is simple, flexible, and suitable for
small to medium-sized datasets, allowing easy integration with existing
academic records without the need for a complex database setup. For future
enhancement, the system can be integrated with a relational database such
as MySQL to support large datasets, improved data security, and multi-user
access.
CHAPTER 5 – IMPLEMENTATION AND TESTING

5.1 Performance Calculation Logic


 MST Marks: 60%
 Assignment Marks: 15%
 Unit Test Marks: 15%
 Attendance: 10%
Performance Levels:
 A: ≥ 75
 B: 50–74
 C: 32–49
 D: < 32

5.2 Testing
Test Case 01:

Valid CSV/Excel upload

Output: Successful analysis

Test Case 02:

Invalid file format

Output: Error message


CHAPTER 6 – CONCLUSION

The Student Performance Analysis System provides an efficient and


automated approach for evaluating academic performance in educational
institutions. The system successfully eliminates the limitations of traditional
manual evaluation methods by reducing human effort and minimizing
calculation errors. By automating the analysis process, the system ensures
accurate, consistent, and timely assessment of student performance.

This project enables faculty members to easily analyze student data and
identify weak, average, and top-performing students at an early stage. The
classification of students into performance categories helps in taking
corrective academic actions such as additional guidance, mentoring, and
performance improvement strategies. The availability of graphical and visual
representations further enhances understanding and interpretation of
academic results.

The system supports data-driven decision-making by providing subject-wise


and overall class performance analysis. It assists faculty members and Heads
of Departments in monitoring academic progress, identifying subject
difficulty levels, and improving teaching methodologies. The use of modern
data analysis tools makes the system reliable and user-friendly.

Although the current version of the system uses CSV and Excel files as data
sources, it has strong potential for future enhancement. The system can be
extended by integrating a database for secure data storage, implementing
login-based access, and adding predictive analytics to forecast student
performance. Overall, the project fulfills its objectives successfully and
demonstrates the effective use of data analytics in improving academic
evaluation systems.
APPENDIX – A (REFERENCES)
 Python Documentation

 Streamlit Documentation

 Pandas Official Website

APPENDIX – B (GLOSSARY)
 CSV: Comma Separated Values

 AI: Artificial Intelligence

APPENDIX – C (FUTURE ENHANCEMENTS)


The Student Performance Analysis System can be further improved
by integrating a relational database such as MySQL for secure and
centralized data storage. Login-based access can be implemented for
faculty and administrators to ensure data privacy. Advanced analytics
and machine learning techniques can also be added to predict future
student performance and provide personalized academic
recommendations. Additionally, a mobile-friendly dashboard can be
developed for easier access and real-time monitoring.
APPENDIX – D (USER MANUAL)

Step No. Action Description


Upload The user uploads the student academic
1 CSV/Excel data file in CSV/Excel format containing
File marks and attendance details.

The user clicks on the Analyze button to


Click
2 initiate performance calculation and data
Analyze
processing.

The system displays analyzed results in


View
3 tabular and graphical format showing
Results
student performance levels.

You might also like