Technical gazette, Vol. 25 No. 2, 2018.
Original scientific paper
https://doi.org/10.17559/TV-20170220135853
Improvement of the Accuracy of Prediction Using Unsupervised Discretization Method: Educational Data Set Case Study
Gabrijela Dimić
orcid.org/0000-0003-4233-540X
; High School of Electrical Engineering and Computer Science, Vojvode Stepe 283, 11000 Belgrade, Serbia
Dejan Rančić
; Faculty of Electronic Engineering, Aleksandra Medvedeva 18, 18000 Niš, Serbia
Ivan Milentijević
; Faculty of Electronic Engineering, Aleksandra Medvedeva 18, 18000 Niš, Serbia
Petar Spalević
; University of Prishtina, Faculty of Technical Sciences, Kneza Miloša 7, 38220 Kosovska Mitrovica, Serbia
Abstract
This paper presents a comparison of the efficacy of unsupervised and supervised discretization methods for educational data from blended learning environment. Naïve Bayes classifier was trained for each discretized data set and comparative analysis of prediction models was conducted. The research goal was to transform numeric features into maximum independent discrete values with minimum loss of information and reduction of classification error. Proposed unsupervised discretization method was based on the histogram distribution and implementation of oversampling technique. The main contribution of this research is improvement of accuracy prediction using the unsupervised discretization method which reduces the effect of ignoring class feature for educational data set.
Keywords
discretization; data mining; educational data set; entropy; equal width binning; histogram; machine learning; oversampling
Hrčak ID:
199137
URI
Publication date:
21.4.2018.
Visits: 2.161 *