Ranking-Based At-Risk Student Prediction Using Federated Learning and Differential Features
Saved in:
| Title: | Ranking-Based At-Risk Student Prediction Using Federated Learning and Differential Features |
|---|---|
| Language: | English |
| Authors: | Shunsuke Yoneda, Valdemar Švábenský, Gen Li, Daisuke Deguchi, Atsushi Shimada |
| Source: | International Educational Data Mining Society. 2025. |
| Availability: | International Educational Data Mining Society. e-mail: admin@educationaldatamining.org; Web site: https://educationaldatamining.org/conferences/ |
| Peer Reviewed: | Y |
| Page Count: | 14 |
| Publication Date: | 2025 |
| Document Type: | Speeches/Meeting Papers Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Higher Education, College Students, Prediction, Textbooks, Electronic Books, Privacy, Confidential Records, Student Behavior, Models, Academic Achievement, Information Management, Grades (Scholastic) |
| Abstract: | Digital textbooks are widely used in various educational contexts, such as university courses and online lectures. Such textbooks yield learning log data that have been used in numerous educational data mining (EDM) studies for student behavior analysis and performance prediction. However, these studies have faced challenges in integrating confidential data, such as academic records and learning logs, across schools due to privacy concerns. Consequently, analyses are often conducted with data limited to a single school, which makes developing high-performing and generalizable models difficult. This study proposes a method that combines federated learning and differential features to address these issues. Federated learning enables model training without centralizing data, thereby preserving student privacy. Differential features, which utilize relative values instead of absolute values, enhance model performance and generalizability. To evaluate the proposed method, a model for predicting at-risk students was trained using data from 1,136 students across 12 courses conducted over 4 years, and validated on holdout test data from 5 other courses. Experimental results demonstrated that the proposed method addresses privacy concerns while achieving performance comparable to that of models trained via centralized learning in terms of Top-n precision, nDCG, and PR-AUC. Furthermore, using differential features improved prediction performance across all evaluation datasets compared to non-differential approaches. The trained models were also applicable for early prediction, achieving high performance in detecting at-risk students in earlier stages of the semester within the validation datasets. [For the complete proceedings, see ED675583.] |
| Abstractor: | As Provided |
| Entry Date: | 2025 |
| Accession Number: | ED675598 |
| Database: | ERIC |
Be the first to leave a comment!
