Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study
Student performance prediction is a critical research challenge in the field of educational data mining. To address this issue, various machine learning methods have been employed with significant success, including instance-based algorithms, decision trees, neural networks, and ensemble methods, am...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Knowledge |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-9585/4/4/28 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850035635795001344 |
|---|---|
| author | Maria Tsiakmaki Georgios Kostopoulos Sotiris Kotsiantis |
| author_facet | Maria Tsiakmaki Georgios Kostopoulos Sotiris Kotsiantis |
| author_sort | Maria Tsiakmaki |
| collection | DOAJ |
| description | Student performance prediction is a critical research challenge in the field of educational data mining. To address this issue, various machine learning methods have been employed with significant success, including instance-based algorithms, decision trees, neural networks, and ensemble methods, among others. In this study, we introduce an innovative approach that leverages the Regularized Greedy Forest (RGF) algorithm within an active learning framework to enhance student performance prediction. Active learning is a powerful paradigm that utilizes both labeled and unlabeled data, while RGF serves as an effective decision forest learning algorithm acting as the base learner. This synergy aims to improve the predictive performance of the model while minimizing the labeling effort, making the approach both efficient and scalable. Moreover, applying the active learning framework for predicting student performance focuses on the early and accurate identification of students at risk of failure. This enables targeted interventions and personalized learning strategies to support low-performing students and improve their outcomes. The experimental results demonstrate the potential of our proposed approach as it outperforms well-established supervised methods using a limited pool of labeled examples, achieving an accuracy of 81.60%. |
| format | Article |
| id | doaj-art-833861ca55554fd1a61487ff51e3cd7f |
| institution | DOAJ |
| issn | 2673-9585 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Knowledge |
| spelling | doaj-art-833861ca55554fd1a61487ff51e3cd7f2025-08-20T02:57:26ZengMDPI AGKnowledge2673-95852024-10-014454355610.3390/knowledge4040028Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case StudyMaria Tsiakmaki0Georgios Kostopoulos1Sotiris Kotsiantis2Educational Software Development Laboratory (ESDLab), Department of Mathematics, University of Patras, 265 04 Rio, GreeceSchool of Social Sciences, Hellenic Open University, 263 31 Patras, GreeceEducational Software Development Laboratory (ESDLab), Department of Mathematics, University of Patras, 265 04 Rio, GreeceStudent performance prediction is a critical research challenge in the field of educational data mining. To address this issue, various machine learning methods have been employed with significant success, including instance-based algorithms, decision trees, neural networks, and ensemble methods, among others. In this study, we introduce an innovative approach that leverages the Regularized Greedy Forest (RGF) algorithm within an active learning framework to enhance student performance prediction. Active learning is a powerful paradigm that utilizes both labeled and unlabeled data, while RGF serves as an effective decision forest learning algorithm acting as the base learner. This synergy aims to improve the predictive performance of the model while minimizing the labeling effort, making the approach both efficient and scalable. Moreover, applying the active learning framework for predicting student performance focuses on the early and accurate identification of students at risk of failure. This enables targeted interventions and personalized learning strategies to support low-performing students and improve their outcomes. The experimental results demonstrate the potential of our proposed approach as it outperforms well-established supervised methods using a limited pool of labeled examples, achieving an accuracy of 81.60%.https://www.mdpi.com/2673-9585/4/4/28educational data miningactive learningpool-based scenariomargin sampling strategyboostingregularized greedy forest algorithm |
| spellingShingle | Maria Tsiakmaki Georgios Kostopoulos Sotiris Kotsiantis Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study Knowledge educational data mining active learning pool-based scenario margin sampling strategy boosting regularized greedy forest algorithm |
| title | Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study |
| title_full | Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study |
| title_fullStr | Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study |
| title_full_unstemmed | Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study |
| title_short | Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study |
| title_sort | exploiting the regularized greedy forest algorithm through active learning for predicting student grades a case study |
| topic | educational data mining active learning pool-based scenario margin sampling strategy boosting regularized greedy forest algorithm |
| url | https://www.mdpi.com/2673-9585/4/4/28 |
| work_keys_str_mv | AT mariatsiakmaki exploitingtheregularizedgreedyforestalgorithmthroughactivelearningforpredictingstudentgradesacasestudy AT georgioskostopoulos exploitingtheregularizedgreedyforestalgorithmthroughactivelearningforpredictingstudentgradesacasestudy AT sotiriskotsiantis exploitingtheregularizedgreedyforestalgorithmthroughactivelearningforpredictingstudentgradesacasestudy |