A Regression Model and a Combination of Academic and Non-Academic Features to Predict Student Academic Performance

Predicting academic performance provides an effective way for students and faculties to monitor their progress. The identification of the most significant features was a key outcome this research, college/university databases from online learning platforms are main data sets used ascertain performance. However, previous research emphasized addition other in prediction Universities’ organizational include non-academic essential determining student success, but no has utilized predict Generally, evaluate binary classification, relationship between predicted classifications true is analyzed, approach can lead loss important information data. Furthermore, avoid such loss, proposes regression model by comparing six algorithms, combining Among various models examined, gradient-boosted trees demonstrated lowest error rate. proposed have been observed impact on performance, making them suitable use predictions.