Case Study
ISSN (Online): 2454-1907
International Journal of Engineering Technologies and Management Research
February 2022 9(2), 64-81
How to cite this article (APA): Henrietta, A. P., and Adekoya, A. F. (2022). Predictive Analytics of Academic Performance of Senior
High School (Shs) Students: A Case Study of Sunyani Shs. International Journal of Engineering Technologies and Management
Research, 9(2), 64-81. doi: 10.29121/ijetmr.v9.i2.2022.1088
64
PREDICTIVE ANALYTICS OF ACADEMIC PERFORMANCE OF SENIOR
HIGH SCHOOL (SHS) STUDENTS: A CASE STUDY OF SUNYANI SHS
Adjei-Pokuaa Henrietta
1
, Adebayo F. Adekoya
2
1, 2
Department of Computer Science and Informatics, University of Energy and Natural Resources, Ghana
Received 03 January 2022
Accepted 01 February 2022
Published 21 February 2022
Corresponding Author
Adjei-Pokuaa Henrietta,
herttydonkor@gmail.com
DOI 10.29121/ijetmr.v9.i2.2022.1088
Funding: This research received no
specific grant from any funding agency in
the public, commercial, or not-for-profit
sectors.
Copyright: © 2022 The Author(s). This is
an open access article distributed under
the terms of the Creative Commons
Attribution License, which permits
unrestricted use, distribution, and
reproduction in any medium, provided
the original author and source are
credited.
ABSTRACT
Due to the availability and increasing adoption of technology in learning
management systems, online admission systems, school management systems, and
educational databases have expanded in recent years.
Motivation/Background: Literature shows that these data contain vital and relevant
information that could be used to monitor and advise students’ so that their
performance could be enhanced. In this study, the random forest algorithm is
proposed to identify and examine the factors that influence students’ performance in
WASSCE. Also, predict the future performance of students in WASSCE.
Method: A total of one thousand five hundred and twenty students’ data were
selected from Sunyani SHS. The results revealed that demographic data (age and
gender) do not influence the performance of students in their final WASSCE.
Results: However, an accuracy of 89.4% with error metrics (RMSE) 0.001639 and
MAPE error of 0.001321 revealed that the proposed model could effectively predict
the performance of students in the WASSCE.
Keywords: Learning Management, Demographic Data, Effectively Predict, Random
Forest Algorithm
1. INTRODUCTION
The size of the educational database keeps proliferating every three
years and these databases contain useful information that can be effectively
employed to improve the academic performance of students Yadav and Pal
(2012). There is a growing focus on institutional data mining by
administrators, educational planners, and managers due to the exponential
growth of educational data. (Anuradha & Velmurugan, 2015). Data mining
techniques have been applied in educational systems to increase the
understanding of the process of learning by concentrating on key issues such
as identifying, mining, and evaluating parameters and variables which are
associated with the learning progress of students Yadav and Pal (2012).
Students’ academic performance is a critical factor in every educational
setting, especially in senior high learning institutes, because educational
institutions are rated based on the academic excellence achieved by their
students and academic staff Mohamed et al. (2016). Forecasting the academic
performance of students in the real world has many challenges, but this has
been made easy with the growth in information and communication
technologies granting access to a large amount of information that could
facilitate the critical decision-making process. Knowledge Discovery in