Student Performance Prediction

Project Overview

This project predicts a student's final G3 score using Machine Learning.

The project uses the Student Performance Dataset and includes data preprocessing, exploratory data analysis, model training, evaluation and prediction.

Technologies Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-learn
• Joblib
• Streamlit

Machine Learning

The project uses Linear Regression and Random Forest Regression models.

The models are evaluated using:

• Mean Absolute Error (MAE)
• R² Score

Model Results

Linear Regression:

• MAE: 0.7651
• R² Score: 0.8487

Random Forest:

• MAE: 0.7651
• R² Score: 0.8429

Linear Regression performed slightly better on this dataset.

Streamlit Application

A Streamlit web application is included for student performance prediction.

Project Structure

Student_Performance_Prediction/

• data/
  • student-por.csv
• main.py
• app.py
• student_performance_model.pkl
• requirements.txt
• README.md

How to Run

Install the required libraries:

pip install -r requirements.txt