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