The Student Performance Predictor is a machine learning project that analyzes student data and predicts their academic performance. By using features such as study hours, attendance, previous scores, and other factors, this model helps identify students who may need additional support and guidance.
- Predicts student performance based on key academic and lifestyle factors
- Preprocessing of raw student data (handling missing values, encoding, scaling)
- Trains and evaluates multiple ML models for accuracy comparison
- Visualizations to explore relationships between study habits and performance
- Easy-to-use notebook for experimenting with the dataset and models
The dataset contains student-related information such as:
- Hours of study
- Attendance percentage
- Previous exam/test scores
- Extra-curricular involvement
- Other academic and personal factors
The dataset was sourced from Kaggle, and is publicly available at: https://www.kaggle.com/datasets/janiobachmann/math-students
- Programming Language: Python
- Libraries: Pandas, NumPy, Matplotlib/Seaborn, Scikit-learn, Jupyter Notebook
student-performance-predictor/
│── student_performance_predictor.ipynb
│── README.md
│── student-mat.csv
- Achieved 83%.
- Visual insights show strong correlation between study hours, attendance, and performance.
- Students with consistent study habits tend to score significantly higher.
- Deploy model as a web app using Flask/Streamlit
- Add more features (sleep hours, social activities, stress levels, etc.)
- Implement deep learning models for improved accuracy
Contributions are welcome! Feel free to fork this repo and submit a pull request with improvements.
This project is licensed under the MIT License.