Educational Data Mining for Student Performance Prediction: A Hybrid Model Perspective

Rama Soni, Abhinav Shukla, Sumati Pathak

2025

Abstract

Data mining technology has significantly improved the ability to extract, store, and interpret enormous quantities of data, even different kinds of data samples. The prediction of students’ academic performance is one of the most fascinating new pathways in the area of educational data mining. Various types of classification methods have been used in studies to predict how well students would perform in their classes, and educational data mining and big data research continues to make these models even more accurate. We developed a hybrid categorisation model to predict the educational performance of students in the Bilaspur City. The proposed hybrid model is a combination of two techniques called ID3 and J48 based classification. In this hybrid method, weak machine learning methods are utilized with a voting strategy to enhance prediction accuracy. Through a dataset of Bilaspur city students, we tested the performance of our hybrid algorithm to predict the academic achievement. To evaluate the effectiveness of the hybrid model, classification accuracy was estimated. The results indicated that the proposed hybrid classifier algorithm achieved an accuracy of 92.40% that lays a good foundation for future improvement and application in educational environments.

Paper Citation

in Harvard Style

Soni R., Shukla A. and Pathak S. (2025). Educational Data Mining for Student Performance Prediction: A Hybrid Model Perspective. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 744-752. DOI: 10.5220/0013872200004919

in Bibtex Style

@conference{icrdicct`2525,
author={Rama Soni and Abhinav Shukla and Sumati Pathak},
title={Educational Data Mining for Student Performance Prediction: A Hybrid Model Perspective},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={744-752},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013872200004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - Educational Data Mining for Student Performance Prediction: A Hybrid Model Perspective
SN - 978-989-758-777-1
AU - Soni R.
AU - Shukla A.
AU - Pathak S.
PY - 2025
SP - 744
EP - 752
DO - 10.5220/0013872200004919
PB - SciTePress