CFP last date
22 April 2024
Reseach Article

Prediction of Students’ Cumulative Grade Point Averages (CGPAs) at Graduation: A Case Study

by Suleiman Khalifa Arafa Ibrahim, Mahmoud Ali Ahmed
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 174 - Number 24
Year of Publication: 2021
Authors: Suleiman Khalifa Arafa Ibrahim, Mahmoud Ali Ahmed
10.5120/ijca2021921149

Suleiman Khalifa Arafa Ibrahim, Mahmoud Ali Ahmed . Prediction of Students’ Cumulative Grade Point Averages (CGPAs) at Graduation: A Case Study. International Journal of Computer Applications. 174, 24 ( Mar 2021), 35-44. DOI=10.5120/ijca2021921149

@article{ 10.5120/ijca2021921149,
author = { Suleiman Khalifa Arafa Ibrahim, Mahmoud Ali Ahmed },
title = { Prediction of Students’ Cumulative Grade Point Averages (CGPAs) at Graduation: A Case Study },
journal = { International Journal of Computer Applications },
issue_date = { Mar 2021 },
volume = { 174 },
number = { 24 },
month = { Mar },
year = { 2021 },
issn = { 0975-8887 },
pages = { 35-44 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume174/number24/31824-2021921149/ },
doi = { 10.5120/ijca2021921149 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:23:00.362328+05:30
%A Suleiman Khalifa Arafa Ibrahim
%A Mahmoud Ali Ahmed
%T Prediction of Students’ Cumulative Grade Point Averages (CGPAs) at Graduation: A Case Study
%J International Journal of Computer Applications
%@ 0975-8887
%V 174
%N 24
%P 35-44
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Predicting student’s performance achievement based on their academic grades continues to be one of the most popular applications of educational data mining and, therefore, it has become a valuable source of knowledge that has been used for different purposes in particular universities. This paper aims to implement the prediction method J48 to predict the students final CGPAs at graduation based on their academic data. For that matter, two different scenarios were investigated in this study. The students’ GPAs from the first 3 years were used for prediction in the first scenario, whereas the students’ GPAs from the first 2 years scores were used in the second scenario. In this study, students academic data for those who did their graduation from the department of Information Technology during the period [2007-2015] , at Comboni College of Science and Technology, SUDAN. As the results indicate, the prediction J48 method performed reasonably well in predicting the student GPA at graduation in both scenarios. According to the 10-fold cross validation test, J48 algorithm produced the accurate prediction result of 83.3333 % for the first scenario. The experiment was repeated for the second scenario. J48 algorithm again produced the accurate prediction results with 81.0345 % was obtained with 10- fold cross validation test. In conclusion, the prediction algorithm J48 in data mining able to accurately predict student CGPA at graduation well in advance, which can identify students needing extra help to improve their academic performance. Moreover, in this study, the Apriori algorithm was used to extract hidden patterns from the graduates’ data. Finally, based on the achieved results, this study could offer helpful feedback and recommendations to the department planners to take corrective measures to assist weak students and in turn, increase their chances of graduating with better grade.

References
  1. Romero, C. and Ventura, S. 2007.Educational data mining: A survey from 1995 to 2005. Expert Systems with Applications, 33(1), 2007, 135–146.
  2. Han, J. and Kamber, M. 2001.Data Mining: Concepts and Techniques. Simon Fraser University, Morgan Kaufmann publishers.
  3. Peña-Ayala, A. 2014. Educational data mining: A survey and a data mining-based analysis of recent works. Expert Systems with Applications, 41(4 PART 1), 1432–1462.
  4. Durairaj, M., & Vijitha, C. 2014. Educational data miningfor prediction of student performance using clusteringalgorithms. International Journal of Computer Science andInformation Technologies (IJCSIT), 5(4), 5987–5991.
  5. Kolo, K. D., Adepoju, S. A., & Alhassan, J. K. 2015. Adecision tree approach for predicting students’ academicperformance. International Journal of Education and ManagementEngineering, 5, 12–19.
  6. Tekin, A. 2014. Early prediction of students’ grade point averages at graduation: A data mining approach. EurasianJournal of Educational Research, (54), 207–226.
  7. Dekker, G.W., M. Pechenizkiy, and J.M. Vleeshouwers. 2009. Predicting students drop out: A case study.EDM ’09-Educational Data Mining: 2nd International Conference on Educational Data Mining, 2009. 2: p. 10.
  8. Sikder, M.F., M.J. Uddin, and S. Halder. 2016. Predicting Students Yearly Performance using Neural Network: A Case Study of BSMRSTU.5th International Conference on Informatics, Electronics and Vision (ICIEV), 2016. 5: p. 6.14.Millán, E., T. Loboda, and J.L. Pérez-de-la-Cruz, Bayesian networks for student model engineerin.Computers and Education. Elsevier Ltd, 2010. 55(4): p. 20.
  9. Witten, I.H. and Frank, E. 2005. Data Mining Practical Machine Learning Tools and Techniques. San Francisco, CA: Morgan Kaufmann Publishers
  10. Muluken Alemu Yehuala, 2015.Application Of Data Mining Techniques For Student Success And Failure Prediction, a Case Of Debre_Markos University.INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 4, ISSUE 04, APRIL 2015.
  11. Mohammed M. Abu Tair, Alaa M. El-Halees, 2012.Mining Educational Data to Improve Students’ Performance:A Case Study. International Journal of Information and Communication Technology Research, Volume 2 No. 2, February 2012.
  12. Fiseha Berhanu and Addisalem Abera, 2015. Students’ Performance Prediction based on their Academic Record. International Journal of Computer Applications (0975 –8887)Volume 131 –No.5, December2015
  13. Sadiq Hussain, Neama Abdulaziz Dahan, Fadl Mutaher Ba-Alwib, Najoua Ribata,Educational,2018. Data Mining and Analysis of Students’ Academic Performance Using WEKA. Indonesian Journal of Electrical Engineering and Computer ScienceVol.9, No.2, February2018, pp. 447~459
  14. C. Romero, J. R. Romero and S. Ventura, 2014. “A survey on pre-processing educational data”, In Educational Data Mining. Springer International Publishing, (2014), pp. 29-64
  15. A. G. Karegowda1, A. S. Manjunath2 and M.A. Jayaram3, 2010. “Comparative study of attribute selection using gain ratio and correlation based feature selection”, International Journal of Information Technology and Knowledge Management, vol. 2, no. 2, (2010), pp. 271-277.
  16. Hӓmӓlӓinen, W., & Vinni, M. 2011.Classifiers for educational data mining. In C. Romero, S. Ventura, M. Pechenizkiy, & R. S. J. d. Baker (Eds.), Handbook of Educational Data Mining (pp. 93-106). Boca Raton, FL: CRC Press. (2011).
  17. Agrawal, R., Imielinski, T., and Swami, A.N. 1993.Mining association rules between sets of items in large databases. In Proceedings of SIGMOD, Washington, DC, (1993). pp. 207–216.
  18. Shrivastava, A.K. and R.N. Panda, 2014.Implementation of Apriori Algorithm using WEKA.KIET International Journal of Intelligent Computing and Informatics, 2014. 1(1): p. 4.
Index Terms

Computer Science
Information Sciences

Keywords

Institutions of Higher Education Educational Data Mining prediction of students’ final CGPAs CCST J48 Algorithm