Student Performance Prediction Model Based on Discriminative Feature Selection

Haixia Lu, Jinsong Yuan


It is a hot issue to be widely studied to determine the factors affecting students' performance from the perspective of data mining. In order to find the key factors that significantly affect students' performance from complex data, this paper pro-poses an integrated Optimized Ensemble Feature Selection Algorithm by Density Peaks (DPEFS). This algorithm is applied to the education data collected by two high schools in China, and the selected discriminative features are used to con-struct a student performance prediction model based on support vector machine (SVM). The results of the 10-fold cross-validation experiment show that, com-pared with various feature selection algorithms such as mRMR, Relief, SVM-RFE and AVC, the SVM student performance prediction model based on the fea-ture selection algorithm proposed in this paper has better prediction performance. In addition, some factors and rules affecting student performance can be extracted from the discriminative features selected by the feature selection algorithm in this paper, which provides a methodological and technical reference for teachers, edu-cation management staffs and schools to predict and analyze the students’ per-formances.


data mining; feature selection; support vector machine (SVM); student perfor-mance prediction model

Full Text:


Copyright (c) 2018 Haixia Lu, Jinsong Yuan

International Journal of Emerging Technologies in Learning. ISSN: 1863-0383
Creative Commons License SPARC Europe Seal
Web of Science ESCI logo Engineering Information logo INSPEC logo DBLP logo ELSEVIER Scopus logo EDiTLib logo EBSCO logo Ulrich's logo Google Scholar logo Microsoft® Academic SearchDOAJ logo