Predictive Model Using a Machine Learning Approach for Enhancing the Retention Rate of Students At-Risk

Student retention is a widely recognized challenge in the educational community to assist institutes formation of appropriate and effective pedagogical interventions. This study intends predict students at-risk low performances during an on-going course, those graduating late than tentative timeline predicting capacity campus. The data constitutes demographics, learning, academic related attributes which are suitable deploy various machine learning algorithms for prediction students. For class balancing, Synthetic Minority Over Sampling Technique, also applied eliminate imbalance award-gap late/timely graduates. Results reveal effectiveness deployed techniques with Long short-term Memory (LSTM) outperforming other models early main contribution this work approach capable enhancing decision making student performance.