Open AccessStudents’ Performance Prediction Modelling using Classification Technique in R
Author(s) -
Thingbaijam Lenin,
N. Chandrasekaran
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b3259.078219
Subject(s) - random forest , naive bayes classifier , computer science , personality , machine learning , quality (philosophy) , order (exchange) , big five personality traits , academic institution , artificial intelligence , focus (optics) , natural language processing , psychology , social psychology , philosophy , physics , epistemology , finance , library science , support vector machine , optics , economics
Among several important tasks an academic institution performs, the most fundamental focus still remains very much on graduating best quality students. It then becomes of paramount importance to identify students whose performance is below par in order to help them to make them better learners. This study makes an earnest attempt to develop an automated system to tackle such a problem using a classification technique of Data Mining implemented with R programming language. Data pertaining to students’ demographic features, their previous academic records and personality traits were analyzed employing Random Forest, Naïve Bayes and K-Nearest Neighbors algorithms. The study shows that Personality, as defined by Myers-Briggs type indicator, influences the student’s performance. Random Forest is found to be the most promising algorithm for developing the students’ performance prediction system.