Fractional-Iterative BiLSTM Classifier : A Novel Approach to Predicting Student Attrition in Digital Academia

Virtual learning circumstances have been observed as consistent growth over the years. The widespread use of online leads to an emerging amount enrollments, also from pupils who quit education scheme previously. However, it earned increased withdrawal rate when compared conventional classrooms. Quick identification is a difficult issue that can be alleviated with help previous models for data evaluation and machine learning. In this research, fractional-Iterative BiLSTM used predicting student's dropout courses high accuracy rate. feature extraction provided by utilizing encoder layer efficiently extracts features based on Statistical features. Fractional-Iterative classifier employed in decoder layer, which effectively performed classification function predict student dropout. accomplishment research evaluated calculating enhancement, developed model achieved increment 96.71% accuracy, 95.31% sensitivity, 97.01% specificity, shows method's efficiency, MSE reduced 0.11%.