Mathematical Modeling and Integration of Machine Learning-Based Prediction System on E-Learning Platform to Improve Students' Academic Performance

Q: What is the main goal of the study on the e-learning platform?

To develop and integrate a machine learning-based system that predicts students’ academic performance and supports adaptive learning interventions.

Q: What student data are used to build the prediction model?

Student activity logs including access frequency, quiz scores, assignment completion time, and forum participation on the e-learning platform.

Q: Which machine learning algorithms are used and how accurate are they?

The study uses logistic regression and a decision tree; decision tree achieves 87.4% prediction accuracy, while logistic regression reaches 81.2%.

Aug 5, 2026

Upload by Seraphina

The study develops and integrates a student academic performance prediction system into an e-learning platform using mathematical modeling combined with machine learning algorithms. A research and development approach guides needs analysis, model development, implementation, and evaluation at Duta Bangsa University. Data from 100 students include activity logs such as access frequency, quiz scores, assignment completion time, and forum participation. Supervised learning models, including logistic regression and decision tree, generate predictions, enabling automated risk notifications and adaptive content recommendations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Background: Growth of e-learning

Challenges: Limited personalization in static platforms

AI-based predictive systems using machine learning

Proposed approach: Modeling and predictive integration

Data sources from student learning behaviors

Machine learning algorithms for risk detection

Algorithm selection considerations

Mathematical Modeling and Integration of Machine LearningBased Prediction System on E-Learning Platform to Improve Students'Academic Performance Anisatul Farida1*, Vihi Atina2, Djatmiko Suwandi3 1Informatics Engineering Study Program, Universitas Duta Bangsa, Indonesia 2Software Engineering Technology Study Program, Universitas Duta Bangsa, Indonesia 3Faculty of Education, Southwest University, China [anisatul_farida@udb.ac.id](anisatul_farida@udb.ac.id) | ABSTRACT | | | | --- | --- | --- | | Article History:
Received : 30-04-2025
Revised : 21-06-2025
Accepted : 24-06-2025
Online : 01-07-2025
Keywords:
Adaptive learning; Machine learning; Mathematical modeling; E-learning;
Academic performance prediction.
| The purpose of this study was to develop and integrate a student academic performance prediction system into an e-learning platform using a mathematical modelling approach combined with machine learning algorithms. The method employed was Research and Development (R&D), encompassing stages of needs analysis, mathematical modelling, development of a machine learning-based prediction system, and implementation and evaluation. The study was conducted at Duta Bangsa University, Surakarta, involving 100 students from the Informatics Engineering study program. Data were collected through the e-learning platform, covering student activity logs such as access frequency, quiz scores, assignment completion time, and forum participation. This behavioral data was then analyzed using supervised learning algorithms, namely logistic regression and decision tree, to build a predictive model for academic performance. The resulting predictive system was integrated into the e-learning platform to deliver risk notifications and adaptive learning material recommendations automatically. To measure the improvement in academic performance, a validated academic achievement test was administered as both a pre-test and a post-test to the experimental group. This test consisted of multiple-choice and short-answer items aligned with the course learning objectives. The results showed that the decision tree model achieved a prediction accuracy of 87.4%, while logistic regression reached 81.2% . Evaluation of the system’s effectiveness using the pre-test and post-test scores revealed a significant increase in students’ academic performance. Statistical analysis with a paired t-test yielded a significance level of p < 0.001, indicating that the adaptive prediction system effectively supports more personalized and impactful learning. This study contributes to the advancement of machine learning-based prediction systems in e-learning by designing and implementing a model that leverages real student activity data. The system enables early detection of academic risks and provides automated, adaptive content recommendations, thus fostering personalized and data-driven learning in higher education. Its practical implementation helps students identify learning weaknesses promptly and receive appropriate supporting materials immediately, promoting proactive and selfregulated learning behavior. | | | | | | | [https://doi.org/10.31764/jtam.v9i3.30994](https://doi.org/10.31764/jtam.v9i3.30994) This is an open access article under the CC–BY-SA license | | | —————————— ◆ —————————— A. INTRODUCTION The development of information technology has brought significant impacts across various sectors of life, including higher education. One of the most notable changes is the adoption of online learning systems, or e-learning, as both an alternative and a complement to face-to-face learning. This trend has intensified in the post-COVID-19 era, when distance learning became the primary choice to maintain academic continuity. E-learning enables students to access learning materials anytime and anywhere, thereby increasing the flexibility and accessibility of education in the digital age (Miraz et al., 2018) . In line with thi

FAQs

What is the main goal of the study on the e-learning platform?

To develop and integrate a machine learning-based system that predicts students’ academic performance and supports adaptive learning interventions.

What student data are used to build the prediction model?

Student activity logs including access frequency, quiz scores, assignment completion time, and forum participation on the e-learning platform.

Which machine learning algorithms are used and how accurate are they?

The study uses logistic regression and a decision tree; decision tree achieves 87.4% prediction accuracy, while logistic regression reaches 81.2%.

Aug 5, 2026

Upload by Seraphina