Comparative Analytics and Predictive Modeling of Student Performance through Data Mining Techniques

11 Pages Posted: 8 Jul 2019

See all articles by Gadisa Namomsa

Gadisa Namomsa

Arba Minch University, Student

Durga Prasad Sharma

AMUIT MOEFDRE under UNDP; ILO-United Nations ; Vrije Universiteit Brussel; Research and Scientific Innovation Society; Research Center MAISM,RTU Kota; UOP University-USA; IACSIT-Singapore; FSFE; Elsevier

Addisu Mulugeta

affiliation not provided to SSRN

Multiple version iconThere are 2 versions of this paper

Date Written: May 3, 2019

Abstract

This research paper is an attempt to predict the performance of the students for improving it in the future through experimental analysis and predictive modeling. The educational repositories / databases can have sufficient facts about learning attitude, capacities and used for discovery of new hidden patterns and knowledge. These hidden patterns and knowledge can be later used for performance enhancement of the students through strategic planning by the university/college authorities. There is lack of predictive studies and models used in Ethiopian context to accurately determine the influencing factors of the students’ performance in academics by categorizing student status in to drop out/fail, poor, good, excellent, or an average performer. Many educational institutions have still not enough strategic plan to predict or determine the student performance in order to improve it, reduce drop out and help to implement the curriculum / academic policies based on student performance and status. This research aims to conduct a comparative analysis and predictive modeling for knowing the student performance status through data mining techniques so as to improve their performance and status. This study used the KDD process model to find and interpret patterns in repositories. Decision tree (J48 and Random Forest), Bayes (NaiveBayes and BayesNet) and Rule-Based (JRip and PART) algorithms are used for classification. The result of this study reveals that the overall accuracy of the tested classifiers is above 80%. In addition, classification accuracy for the different classes reveals that the predictions are worst for fail class and fairly good for the average class. The J48 and JRip classifiers relatively produce the highest classification accuracy for the average performer/ status. Finally, the study suggests that data mining can be used as significant the technique to figure out student performance based on salient factors affecting.

Keywords: Data Mining, Decision Tree, Prediction, Naive Bayes, Rule-Based

Suggested Citation

Namomsa, Gadisa and Prasad Sharma, Durga and Mulugeta, Addisu, Comparative Analytics and Predictive Modeling of Student Performance through Data Mining Techniques (May 3, 2019). Available at SSRN: https://ssrn.com/abstract=3382511 or http://dx.doi.org/10.2139/ssrn.3382511

Gadisa Namomsa

Arba Minch University, Student ( email )

Ethiopia

Durga Prasad Sharma (Contact Author)

AMUIT MOEFDRE under UNDP ( email )

ILO-United Nations ( email )

Vrije Universiteit Brussel ( email )

Belgium

Research and Scientific Innovation Society ( email )

India

Research Center MAISM,RTU Kota ( email )

India

UOP University-USA ( email )

IACSIT-Singapore ( email )

Singapore

FSFE ( email )

Germany

Elsevier ( email )

Netherlands

Addisu Mulugeta

affiliation not provided to SSRN

Register to save articles to
your library

Register

Paper statistics

Downloads
10
Abstract Views
73
PlumX Metrics