This is a machine learning project where I built a model to predict whether a student will pass or fail based on their scores and background information.
The goal is to help understand which factors affect student performance and make predictions based on:
- Gender
- Lunch type
- Test preparation
- Math, Reading, and Writing scores
- Parental level of education
The project includes:
- Data cleaning and exploration
- Visualisations to find patterns
- Model training (Logistic Regression, Random Forest, etc.)
- Performance evaluation
- A simple Streamlit web app for interaction
- Python
- Pandas, NumPy
- Seaborn & Matplotlib (for visualisation)
- Scikit-learn (for modelling)
- Streamlit (for the web app)
- Git & GitHub
-
Clone the repo:
git clone https://github.com/your-username/student-performance-prediction.git
-
Install the required libraries:
pip install -r requirements.txt
-
Run the Streamlit app:
streamlit run app.py
The model uses real student data and shows how different factors impact results. It also handles class imbalance using techniques like class weighting or SMOTE.
This project is open source and available under the MIT License.