A Case-Study Comparison of Machine Learning Approaches for Predicting Student's Dropout from Multiple Online Educational Entities - article findings

Aug 4, 2026

Predicting student dropout is a crucial task in online education. Traditionally, each educational entity trains and uses its own local prediction model from its own data, which may be infeasible when data, infrastructure, or resources are limited. The study compares machine learning strategies that share data and/or models across entities, including centralized learning, transfer learning, and federated learning. Using Moodle-based data from three distinct LMS servers, it evaluates dropout prediction with deep learning and reports comparative benefits and drawbacks, showing that repurposed and stacked transfer learning and centralized approaches can match or exceed locally trained models across most entities.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Introduction

Student dropout prediction in learning analytics and EDM

Binary classification framing and algorithms

Methods and Approaches

Centralized learning

Transfer learning strategies

Federated learning

Experimental Setup and Evaluation

Data from multiple Moodle entities

Deep learning-based classifier

Results and Discussion

Performance comparison across entities

Benefits, drawbacks, and recommendations

algorithms Article A Case-Study Comparison of Machine Learning Approaches for Predicting Student's Dropout from Multiple Online Educational Entities Jos² Manuel Porras, Juan Alfonso Lara , Cristâbal Romero * and Sebasti¡n Ventura Citation: Porras, J.M.; Lara, J.A.; Romero, C.; Ventura, S. A Case-Study Comparison of Machine Learning Approaches for Predicting Student's Dropout from Multiple Online Educational Entities. Algorithms 2023, 16, 554. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)a16120554 Academic Editor: Ioannis Tsoulos Received: 7 November 2023 Revised: 1 December 2023 Accepted: 1 December 2023 Published: 3 December 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . Department of Computer Science, University of Cordoba, 14071 Cârdoba, Spain; [i82poroj@uco.es](i82poroj@uco.es) (J.M.P.); [juan.lara@uco.es](juan.lara@uco.es) (J.A.L.); [sventura@uco.es](sventura@uco.es) (S.V.) * Correspondence: cromero@uco.es Abstract: Predicting student dropout is a crucial task in online education. Traditionally, each educational entity (institution, university, faculty, department, etc.) creates and uses its own prediction model starting from its own data. However, that approach is not always feasible or advisable and may depend on the availability of data, local infrastructure, and resources. In those cases, there are various machine learning approaches for sharing data and/or models between educational entities, using a classical centralized machine learning approach or other more advanced approaches such as transfer learning or federated learning. In this paper, we used data from three different LMS Moodle servers representing homogeneous different-sized educational entities. We tested the performance of the different machine learning approaches for the problem of predicting student dropout with multiple educational entities involved. We used a deep learning algorithm as a predictive classiﬁer method. Our preliminary ﬁndings provide useful information on the beneﬁts and drawbacks of each approach, as well as suggestions for enhancing performance when there are multiple institutions. In our case, repurposed transfer learning, stacked transfer learning, and centralized approaches produced similar or better results than the locally trained models for most of the entities. Keywords: dropout prediction; predictive analytics; transfer learning; federated learning 1. Introduction One important task in learning analytics (LA) [1] and educational data mining (EDM) [2] research is student dropout prediction (SDP) . SDP is an important educational problem because of the high dropout rate, mainly from e-learning environments. The recent spread of online courses—with enormous numbers of enrolled students, only a fraction of whom complete their studies successfully—has led to increased attention to this problem. As a consequence, there is a growing interest in the adoption of automated systems for predicting student dropout. Automated methodologies have also caught the attention of researchers, particularly in the area of machine learning. Students doing online degree programs have a higher chance of dropping out than those attending conventional classroom environments. According to [3], 40–80% of online students drop out from online classes. Moreover, students may leave courses at any time without notice or further repercussions. Therefore, it is of paramount interest to ﬁnd more effective methods of addressing the problem of dropout in e-learning environments. The speciﬁc objective of SDP in e-learning environments is to model student behavior interacting with e-learnin

FAQs

Why is dropout prediction important in online education?

High dropout rates in e-learning environments make early, automated prediction crucial. It helps identify students likely not to finish courses or degrees.

What problem does the paper address about traditional local modeling?

Local approaches require each entity to collect enough data and resources to train its own model. This may be difficult due to limited data availability and infrastructure constraints.

Which machine learning approaches are compared for handling multiple educational entities?

The paper compares centralized learning, repurposed transfer learning, stacked transfer learning, and federated learning approaches for dropout prediction across multiple entities.

Aug 4, 2026

Upload by Ava Thompson