DEVELOPMENT OF AN AI-DRIVEN STUDENT ACADEMIC PERFORMANCE PREDICTION AND SUPPORT APP

This project developed a mobile application that predicts students' Cumulative Grade Point Average (CGPA) using machine learning models, addressing the challenge of providing accurate and personalized academic performance insights. The problem stems from the need for students to better understand their academic trajectories and make informed decisions about their studies. The primary objective is to build an efficient prediction model that utilizes student data, including GPA, attendance, and study rate, to forecast CGPA with high accuracy. The methodology involves data collection, preprocessing, and feature engineering, followed by the implementation of three machine learning models: Linear Regression, Decision Tree, and Gradient Boosting. These models were evaluated based on RMSE and R-squared values, with Gradient Boosting achieving the best performance, providing a 97% prediction accuracy. Results show that the Gradient Boosting model significantly outperforms the others with an RMSE of 0.0934 and R-squared of 0.9905, providing more reliable predictions. In conclusion, the results the app provides accurate, consistent academic predictions based on collected data.