This project explores how we can predict whether a student is likely to graduate, drop out, or stay enrolled . We used powerful ensemble learning models like XGBoost, AdaBoost, and CatBoost and fine tuned them to get the best results. To make sure our improvements were real , we ran hypothesis tests and the Wilcoxon signed-rank test
The aim is simple, build a tool that helps educators spot at-risk students early so they can step in and give the right support, helping more students succeed.