Evolutionary Algorithm Based Feature Subset Selection for Students Academic Performance Analysis

Educational Data Mining (EDM) is an emergent discipline that concentrates on the design of self-learning and adaptive approaches. Higher education institutions have started to utilize analytical tools improve students’ grades retention. Prediction performance a difficult process owing massive quantity educational data. Therefore, Artificial Intelligence (AI) techniques can be used for data mining in big environment. At same time, EDM, feature selection becomes necessary creation subsets. Since affects predictive any model, it important elaborately investigate outcome model related techniques. With this motivation, paper presents new Metaheuristic Optimization-based Feature Subset Selection with Optimal Deep Learning (MOFSS-ODL) predicting performance. In addition, proposed uses isolation forest-based outlier detection approach eliminate existence outliers. Besides, Chaotic Monarch Butterfly Optimization Algorithm (CBOA) highly features low complexity high Then, sailfish optimizer stacked sparse autoencoder (SFO-SSAE) utilized classification The MOFSS-ODL tested against benchmark student’s set from UCI repository. A wide-ranging simulation analysis portrayed improved technique over recent approaches terms different measures. Compared other methods, experimental results prove does great job academic progress, accuracy 96.49%.