Student performance prediction using classification data mining techniques.
Year: 2016
Type: preprint
Abstract: Students opting engineering as their disciple is increasing rapidly. But due to various factors and inappropriate primary education in India dropout rates are high. Students are unable to excel in core engineering subjects which are complex and mathematical, hence mostly get drop / keep term (kt) in that subject. With the help of data mining techniques we can predict the performance of students in terms of grades and dropout for a subject. This paper compares various techniques such as na\ive Bayes, LibSVM, J48, random forest, and JRip and try to choose one of them as per our needs and their accuracy. Based on the rules obtained from this technique(s), we derive the key factors influencing student performance.
Source: arXiv (Cornell University)
Authors: Muhammed Salman Shamsi, Jhansi Lakshmi
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W2471189432
