Predicting individual learning performance using machine?learning hybridized with the teaching?learning?based optimization

Reliable prediction of individual learning performance can facilitate timely support to students and improve the experience. In this study, two well-known machine-learning techniques, that is, vector machine (SVM) artificial neural network (ANN), are hybridized by teaching–learning-based optimizer (TLBO) reliably predict student exam (fail-pass classes final scores). For defined classification regression problems, TLBO algorithm carries out feature selection process both ANN SVM techniques in which optimal combination input variables is determined. Moreover, architecture determined using parallel process. Finally, four hybrid models containing anonymized information on discrete continuous were developed a comprehensive data set for analytics. This study provides scientific utility developing TLBO, predictions performance. practice, help advise about their academic progress take appropriate actions such as dropping units subsequent teaching periods. It also scholarship providers monitor provision support.