Ensemble Machine Learning Model for University Students’ Risk Prediction and Assessment of Cognitive Learning Outcomes

One of the biggest challenges in higher educational institutions is to avoid students’ failures. Globally student dropout a serious issue. Risk dropouts can be identified at an earlier stage using machine learning classifiers, as they have gained more popularity both academia and industry. The research team suggests that early prediction facilitates educators education administrators take necessary measures prevent dropouts. Data for were collected from 530 Indian students when engaged online during pandemic crisis. This work involves two phases. In first phase, hybrid ensemble strategy focused integrates powerful algorithms namely Random Forest (RF) eXtreme Gradient Boosting (XGBoost) at-risk prediction. result fast procedure classification which competitive accuracy highly robust. Prediction models are developed learning, furthermore combined into single meta-model, provides best outcomes enable predictive analysis. Moreover, it correctly classified regarding accuracy, precision, recall F1-score with values 93%, 91.52%, 96.42% 93.91% respectively. second model deployed by creating web application using. Net framework sense sentiments Azure cognitive services text analytics (Application Programming Interface) API detecting behavioral environment.