Supervised data mining approach for predicting student performance

Wan Fairos Wan Yaacob, Syerina Azlin Md Nasir, Wan Faizah Wan Yaacob, Norafefah Mohd Sobri

Abstract


Data mining approach has been successfully implemented in higher education and emerge as an interesting area in educational data mining research. The approach is intended for identification and extraction of new and potentially valuable knowledge from the data. Predictive model developed using supervised data mining approach can derive conclusion on students' academic success. The ability to predict student’s performance can be beneficial for innovation in modern educational systems. The main objective of this paper is to develop predictive models using classification algorithm to predict student’s performance at selected university in Malaysia. The prediction model developed can be used to identify the most important attributes in the data. Several predictive modelling techniques of K-Nearest Neighbor, Naïve Bayes, Decision Tree and Logistic Regression Model models were used to predict student’s performance whether excellent or non-excellent.  Based on accuracy measure, precision, recall and ROC curve, results show that the Naïve Bayes outperform other classification algorithm.  The Naïve Bayes reveals that the most significant factors contributing to prediction of excellent students is when the student scores A+ and A in Multivariate Analysis; A+, A and A- in SAS Programming and A, A- and B+ in ITS 472.

Keywords


Data Mining, Classification technique, Predictive model, Student performance

Full Text:

PDF


DOI: http://doi.org/10.11591/ijeecs.v16.i3.pp1584-1592
Total views : 97 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

shopify stats IJEECS visitor statistics