A Student Performance Prediction Model Using Data Mining Technique

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Predicting performance is very significant in the education world nowadays. This paper will describe the process of doing a prediction of student performance by using data mining technique. 257 data sets were taken from the student of semester 6 KPTM that involved four (4) academic programs which are Diploma in Computer System and Networking, Diploma in Information Technology, Diploma in Business Management and Diploma in Accountancy. Knowledge Discovery in Database (KDD) was used as a guide to the process of finding and extracting a knowledge from the dataset. A decision tree and linear regression were used to analyze the dataset based on variables selected. The variables used are Gender, Financing, SPM, GPASem1, GPASem2, GPASem3, GPASem4, GPASem5 and CGPA as a dependent variable. The result from this indicate the significant variable that contribute most to the students’ performance. Based on the analysis, the decision tree shows that GPASem1 has a strong significant to the CGPA final semester of the student and the prediction accuracy is 82%. The linear regression shows that the GPA for each semester has a highly significant with the dependent variable with 96.2% prediction accuracy. By having this information, the management of KPTM can make a plan to ensure that the student can maintain a good result and at the same time to make a strategic plans for those without a good result.



  • Keywords

    Data mining, Knowledge Discovery in Database, Prediction, Student performance, Decision tree

  • References

      [1] F. Grivokostopoulou, I. Perikos, and I. Hatzilygeroudis, “Utilizing semantic web technologies and data mining techniques to analyze students learning and predict final performance,” Proc. IEEE Int. Conf. Teaching, Assess. Learn. Eng. Learn. Futur. Now, TALE 2014, no. December, pp. 488–494, 2015.

      [2] A. Ktona, D. Xhaja, and I. Ninka, “Extracting Relationships between Students’ Academic Performance and Their Area of Interest Using Data Mining Techniques,” 2014 Sixth Int. Conf. Comput. Intell. Commun. Syst. Networks, pp. 6–11, 2014.

      [3] M. T. Devasia, M. V. T. P, and V. Hegde, “Prediction of Students Performance using Educational Data Mining.”

      [4] T. Mishra, D. Kumar, and S. Gupta, “Mining students’ data for prediction performance,” Int. Conf. Adv. Comput. Commun. Technol. ACCT, pp. 255–262, 2014.

      [5] N. Buniyamin, U. Bin Mat, and P. M. Arshad, “Educational data mining for prediction and classification of engineering students achievement,” 2015 IEEE 7th Int. Conf. Eng. Educ. ICEED 2015, pp. 49–53, 2016.

      [6] P. M. Arsad, N. Buniyamin, and J. A. Manan, “A neural network students’ performance prediction model (NNSPPM),” Smart Instrumentation, Meas. Appl. (ICSIMA), 2013 IEEE Int. Conf., no. November, pp. 1–5, 2013.

      [7] J. Jacob, K. Jha, P. Kotak, and S. Puthran, “Educational Data Mining techniques and their applications,” 2015 Int. Conf. Green Comput. Internet Things, ICGCIoT 2015, pp. 1344–1348, 2016




Article ID: 11214
DOI: 10.14419/ijet.v7i2.15.11214

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.