Predicting At-Risk Programming Students in Small Imbalanced Datasets using Synthetic Data

2025-05-21

AI Summary

Early identification of at-risk students in introductory programming courses remains challenging, particularly given small-scale, highly imbalanced real-world educational data (N=379; 15% failure rate). Method: This study is the first to systematically apply synthetic minority oversampling techniques—SMOTE and ADASYN—to programming education early-warning scenarios. We built predictive models using logistic regression, random forest, and XGBoost, and employed SHAP for interpretable feature importance analysis to inform formative assessment design. Contribution/Results: Synthetic data augmentation significantly improved recall for failing students by +28.6%, demonstrating the effectiveness and deployability of early-warning models in authentic classroom settings. The approach provides a novel methodology and practical pathway for precise, timely interventions in low-sample, class-imbalanced educational contexts.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Programming
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study is part of a larger project focused on measuring, understanding, and improving student engagement in programming education. We investigate whether synthetic data generation can help identify at-risk students earlier in a small, imbalanced dataset from an introductory programming module. The analysis used anonymised records from 379 students, with 15% marked as failing, and applied several machine learning algorithms. The first experiments showed poor recall for the failing group. However, using synthetic data generation methods led to a significant improvement in performance. Our results suggest that machine learning can help identify at-risk students early in programming courses when combined with synthetic data. This research lays the groundwork for validating and using these models with live student cohorts in the future, to allow for timely and effective interventions that can improve student outcomes. It also includes feature importance analysis to refine formative tasks. Overall, this study contributes to developing practical workflows that help detect disengagement early and improve student success in programming education.

Problem

• Identifying at-risk students in small imbalanced programming datasets
• Improving early detection using synthetic data generation methods
• Enhancing machine learning performance for student failure prediction

Innovation

• Using synthetic data for imbalanced datasets
• Machine learning to identify at-risk students
• Feature analysis to refine formative tasks