Student Performance Indicator

Project Overview This project aims to accurately predict student performance through an end-to-end machine learning pipeline. By leveraging various regression techniques, we have developed a model that achieves an R^2 score of 88.57%, indicating a high level of accuracy in predicting student outcomes. This predictive model can serve as a vital tool for educational institutions seeking to identify and support students at risk of underperforming.

Features Comprehensive Data Analysis: Utilization of advanced data preprocessing and analysis techniques to understand key factors influencing student performance. Multiple Regression Models: Exploration of various regression models, including CatBoost, AdaBoost, Linear Regression, Logistic Regression, Lasso, Ridge, RandomForest, K-Nearest Regressor, XGBoost Regressor, to identify the most effective predictor. Hyperparameter Tuning: Application of systematic hyperparameter tuning to optimize model performance. Model Deployment: Deployment of the final model on AWS Beanstalk for easy access and scalability. Continuous Integration/Continuous Deployment (CI/CD): Implementation of AWS CodePipeline for streamlined updates and deployment processes.

Getting Started To utilize this project, follow the steps below:

Clone the Repository: Clone this project to your local machine. Install Dependencies: Ensure all required libraries and dependencies are installed. Run the Application: Launch the application to start predicting student performance. Technologies Used Machine Learning: Scikit-learn, CatBoost, XGBoost, etc. Deployment: AWS Beanstalk CI/CD: AWS CodePipeline Data Analysis: Pandas, NumPy Contributing Your contributions are welcome! Please feel free to submit a pull request or open an issue for any bugs or feature suggestions.