https://github.com/messi10tom/ai-based-grade-prediction

GDSC task-1: Build a model to predict a student’s final grade based on features such as attendance, participation, assignment scores, and exam marks.
https://github.com/messi10tom/ai-based-grade-prediction

ai data-analysis data-science regression streamlit

Last synced: about 2 months ago
JSON representation

GDSC task-1: Build a model to predict a student’s final grade based on features such as attendance, participation, assignment scores, and exam marks.

• Host: GitHub
• URL: https://github.com/messi10tom/ai-based-grade-prediction
• Owner: messi10tom
• License: mit
• Created: 2024-12-11T16:58:13.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-12-26T07:57:33.000Z (over 1 year ago)
• Last Synced: 2025-04-06T17:52:11.323Z (about 1 year ago)
• Topics: ai, data-analysis, data-science, regression, streamlit
• Language: Jupyter Notebook
• Homepage: https://grade-prediction.streamlit.app/
• Size: 1.13 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# AI-Based Grade Prediction

![Project Banner](./doc/banner.webp)

[![License: CC BY 4.0](https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by/4.0/)

[![Python](https://img.shields.io/badge/Python-3.8%2B-blue.svg)](https://www.python.org/downloads/release/python-380/)

[![Streamlit](https://img.shields.io/badge/Streamlit-0.84.0-red.svg)](https://streamlit.io/)

## Problem Statement

Build a model to predict a student’s final grade based on features such as attendance, participation, assignment scores, and exam marks.

## Approach

1. **Data Collection**: Utilized the Student Performance Dataset from the UCI Machine Learning Repository.

2. **Data Preprocessing**: Cleaned and processed the data to handle categorical variables.

3. **Model Training**: Trained an Artificial Neural Network(ANN) for regression.

4. **Evaluation**: Evaluated models using RMSE and classification metrics like accuracy.

5. **Feature Analysis**: Analyzed feature importance to identify key contributors to performance.



6. **Productization**: Developed a Streamlit web app for user interaction.

## Results

- **Model Performance**:

    - ANN Model: RMSE = 0.2576

## Challenges

- **Feature Engineering**: Created new features to improve model performance.

- **Model Overfitting**: Implemented regularization techniques to mitigate overfitting.

## Installation

1. Clone the repository:

    ```bash

        git clone https://github.com/messi10tom/AI-Based-Grade-Prediction.git

        cd AI-Based-Grade-Prediction

    ```

2. Create and activate a virtual environment:

    ```bash

        python3 -m venv venv

        source venv/bin/activate

    ```

3. Install the required packages:

    ```bash

        pip install -r requirements.txt

    ```

## Usage

1. **Running the Web App**:

    ```bash

        streamlit run src/app.py

    ```

## Screenshots

### Training logs

![Training Logs](./train/train%20log.png)

![Web App](./doc/streamlit%20UI.png)

## License

This project is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0). See the [LICENSE](LICENSE) file for details.

---

For further details, visit the [dataset page on UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/Student+Performance).