Evaluating the Impact of Data Augmentation on Predictive Model Performance

Valdemar Svabensky, Conrad Borchers, Elizabeth B. Cloude, Atsushi Shimada

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In supervised machine learning (SML) research, large training datasets are essential for valid results. However, obtaining primary data in learning analytics (LA) is challenging. Data augmentation can address this by expanding and diversifying data, though its use in LA remains underexplored. This paper systematically compares data augmentation techniques and their impact on prediction performance in a typical LA task: prediction of academic outcomes. Augmentation is demonstrated on four SML models, which we successfully replicated from a previous LAK study based on AUC values. Among 21 augmentation techniques, SMOTE-ENN sampling performed the best, improving the average AUC by 0.01 and approximately halving the training time compared to the baseline models. In addition, we compared 99 combinations of chaining 21 techniques, and found minor, although statistically significant, improvements across models when adding noise to SMOTE-ENN (+0.014). Notably, some augmentation techniques significantly lowered predictive performance or increased performance fluctuation related to random chance. This paper's contribution is twofold. Primarily, our empirical findings show that sampling techniques provide the most statistically reliable performance improvements for LA applications of SML, and are computationally more efficient than deep generation methods with complex hyperparameter settings. Second, the LA community may benefit from validating a recent study through independent replication.

Original languageEnglish
Title of host publication15th International Conference on Learning Analytics and Knowledge, LAK 2025
PublisherAssociation for Computing Machinery, Inc
Pages126-136
Number of pages11
ISBN (Electronic)9798400707018
DOIs
Publication statusPublished - Mar 3 2025
Event15th International Conference on Learning Analytics and Knowledge, LAK 2025 - Dublin, Ireland
Duration: Mar 3 2025Mar 7 2025

Publication series

Name15th International Conference on Learning Analytics and Knowledge, LAK 2025

Conference

Conference15th International Conference on Learning Analytics and Knowledge, LAK 2025
Country/TerritoryIreland
CityDublin
Period3/3/253/7/25

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Education
  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Evaluating the Impact of Data Augmentation on Predictive Model Performance'. Together they form a unique fingerprint.

Cite this