Using Ensemble Machine Learning and Feature Engineering to Increase the Accuracy of Predicting Learners’ Performance in an Online Educational Environment

Aug 5, 2026

Upload by Liam

Online training has expanded as an effective instructional approach, increasing the need for timely monitoring of learner progress and engagement. Accurately predicting academic performance in online courses supports learners who face the risk of academic decline. This study develops a robust predictive model using ensemble machine learning and feature engineering on a DEEDS dataset of real-time learner interactions, extracting and selecting informative features. Multiple boosting and stacking strategies are evaluated with common tree-based and gradient models, achieving high accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

Introduction

Learning analytics types

Importance of predicting learner performance

Interdisciplinary Journal of Virtual Learning in Medical Sciences Original Article Using Ensemble Machine Learning and Feature Engineering to Increase the Accuracy of Predicting Learners’ Performance in an Online Educational Environment Seyede Fatemeh Noorani1*, Maryam Karimi2, Zahra Gholijafari1 1Department of Information Technology and Computer Engineering, Payame Noor University, Tehran, Iran 2Department of Computer Sciences, Faculty of Mathematical Sciences, Shahrkord, Iran ABSTRACT Background: Online training has gained popularity as an effective teaching method, necessitating diligent monitoring of learner progress and engagement. The challenge of predicting academic performance in online courses is crucial for supporting learners at risk of academic loss. This study aimed to develop a robust model for predicting learners’ performance using ensemble machine learning and feature engineering techniques. Methods: This research employed a classification approach based on the Digital Electronic Education and Design Suite (DEEDS) dataset, which records real-time interactions of learners within an online educational environment. The dataset analyzed in this research included activity logs from 115 undergraduate students majoring in computer engineering who participated in a digital electronics course at the University of Genoa, Italy, between September and December 2015. Various machine learning algorithms, including Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Light Gradient-Boosting Machine (LightGBM), and eXtreme Gradient Boosting (XGBoost), were applied. The study also utilized ensemble learning methods such as Boosting and Stacking to enhance prediction accuracy. Feature engineering techniques were implemented to extract and select relevant features from the dataset, leading to the development of a predictive model. Results: The proposed model achieved an accuracy of 97.43%, a precision of 96.20%, and an F1-score of 98.06%, indicating an acceptable predictive capability. Notably, the findings revealed that feature selection significantly enhanced performance; in the absence of feature selection, the accuracy dropped to 92.15% . Additionally, ensemble methods like Boosting and Stacking provided a 15% enhancement in prediction accuracy compared to traditional approaches. Overall, the integration of feature engineering and ensemble techniques acceptably optimized the model’s ability to predict learners’ academic performance in online educational settings. Conclusion: This research validates the effectiveness of employing ensemble machine learning techniques and feature engineering in predicting learners’ academic performance in online education. Future studies should explore additional ensemble methods and incorporate diverse feature types to enhance prediction accuracy. Keywords: Information Science, Supervised Machine Learning, Educational, Data Mining, Dimensionality Reduction, Computer-Assisted *Corresponding author: Seyede Fatemeh Noorani, Department of Information Technology and Computer Engineering, Payame Noor University, Tehran, Iran Tel: +98 21 22455076 Email: [sf.noorani@pnu.ac.ir](sf.noorani@pnu.ac.ir) Please cite this paper as: Noorani SF, Karimi M, Gholijafari Z. Using Ensemble Machine Learning and Feature Engineering to Increase the Accuracy of Predicting Learners’ Performance in an Online Educational Environment. Interdiscip J Virtual Learn Med Sci. 2024;15(4):369-387.doi:10.30476/ ijvlms.2024.101157.1279. Received: 23-12-2023 Revised: 04-11-2024 Accepted: 21-11-2024 Interdisciplinary Journal of Virtual Learning in Medical Sciences (IJVLMS) is licensed under a Creative Commons AttributionNoDerivatives 4.0 International License. [https://creativecommons.org/licenses/by-nd/4.0](https://creativecommons.org/licenses/by-nd/4.0) Using Ensemble Machine Learning to Improve Predictions of Learners' Performance in E-learning Noorani SF et al. Introduct

FAQs

What problem does the study address in online education?

The study targets the challenge of predicting learners’ academic performance in online courses to support learners who may be at risk of academic loss.

Which dataset and modeling approach are used to build the prediction model?

The model is built using the DEEDS dataset with a classification approach, applying several machine learning algorithms and ensemble learning methods such as boosting and stacking.

What impact did feature selection and ensemble learning have on performance?

Feature selection substantially improved results, and ensemble methods like boosting and stacking increased prediction accuracy by about 15% compared with traditional approaches.

Aug 5, 2026

Upload by Liam