Enhancement of Students' Academic Performance and Association Rule Mining

Authors

  • Muhammad Saqib Department of Computing, Arden University, Berlin Campus, Berlin 10963, Germany.
  • Muhammad Aadil Computing Department, IQRA National University, Peshawar, 25100, Pakistan.
  • Hamail Raza Zaidi Computing Department, IQRA National University, Peshawar, 25100, Pakistan.

Keywords:

Machine Learning, Data Mining, E-Learning

Abstract

Data mining techniques have revolutionized the process of finding insights from data and, thus making it easier for managers to make better decisions. Relevant tools and appropriate methodologies have enabled several organizations to extract actionable knowledge available within a massive amount of data. This research study is an attempt to investigate the association among several factors and the academic performance of college/university students. We have discussed and analysed the potential benefits of using a few techniques of data mining in the education sector, and thus established an understanding of how those techniques can effectively help learners in overall academic performance improvement. The research started with a thorough literature review to support arguments. One of the techniques, i.e., Association Rule Mining (ARM), is explored further and compared with a few other techniques in this specific research. It has been found an effective approach in finding associations and discovering patterns in the data. The study also reveals that appropriate use of association rule mining and decision trees with influencing study elements may offer a high level of prediction accuracy of students’ achievement, while concluding, it is recommended that other Data Mining algorithms may be taken into consideration for further such discoveries.

Downloads

Published

2025-09-30