BiLSTM model predicts distance-education students' academic failure risk by Week 6 from LMS weekly interaction logs, reporting 91.4% accuracy and 92.6% recall
This study develops a Bidirectional Long Short-Term Memory (BiLSTM) deep learning model that predicts student academic performance and failure risk from weekly interaction patterns in a Learning Management System (LMS), using a dataset of interaction logs from 1,250 distance education students over one semester with features such as material access frequency, forum participation, and assignment submission timing, and reports 91.4% accuracy, 89.2% precision, and 92.6% recall as early as Week 6 of the course, enabling educators to implement timely pedagogical interventions to reduce dropout rates in digital and distance learning environments.