This project explores the use of machine learning to predict student academic performance based on historical data. It focuses on analyzing key features, preprocessing data, and applying predictive models to evaluate how well students are likely to perform.
The notebook (Prediction_V2.ipynb) walks through data exploration, feature engineering, model training, and performance evaluation, with visualizations to support insights.
- pandas – data manipulation and preprocessing
- numpy – numerical computations
- matplotlib / seaborn – data visualization
- scikit-learn – machine learning models and evaluation metrics
- jupyter – interactive development environment
- Data cleaning and preprocessing
- Exploratory data analysis with visualizations
- Model training and comparison
- Evaluation of prediction accuracy and performance metrics