Enhancing Student'sPerformance Classification Using Ensemble Modeling

Abstract

A precise prediction of student performance is an important aspect withineducational institutions to improve results and provide personalized support ofstudents.However, the predication accuracy of student performance considers anopenissue within education field.Therefore, thispaper proposes a developedapproachto identifyperformance of students using a group modeling. This approach combinesthe strengths of multiple algorithms including random forest (RF), decision tree (DT), AdaBoosts, and support vector machine (SVM). Afterward, thelastensemble estimatesas one of the bets logistic regressionmethodswas utilizedto create a robust and reliable predictive modelbecause it considers The experiments were evaluated usingtheOpen University Learning Analytics Dataset (OULAD)benchmark dataset.The OULADdataset considersa comprehensive dataset containingvarious characteristics related to the student’sactivitiesthereby five cases based on the utilized dataset were investigated. Theexperimentresults showed that the proposed ensemble modelpresented its ability with accurate results to classify student performanceby achieving95%of accuracy rate. As a result, the proposed model exceeded the accuracy of individual basic models by using the strengths of variousalgorithms toimprovethe generalization byreducingthe potential weaknesses of individual models. Consequently, the education institutescan easilyidentify students who may need additional support and interventions to improve their academic performance