Enhancing Student Performance Prediction In CS1 Via In-Class Coding

2025-10-22

AI Summary

Students in introductory computer science (CS1) courses exhibit heterogeneous academic backgrounds, making early identification of at-risk learners challenging. Method: This paper proposes leveraging in-class coding exercise behavioral data—such as submission frequency, debugging duration, and code revision patterns—integrated with conventional academic indicators (e.g., attendance, assignment scores) to build machine learning models for early performance prediction. Using real-world CS1 instructional data, we train and evaluate predictive models on the first 3–5 weeks of course activity. Results: Our model achieves an AUC of ≥0.82 using only early coding exercise features, significantly outperforming baseline models relying solely on traditional metrics. This work provides the first systematic empirical validation that lightweight, ecologically valid in-class programming behaviors are strongly predictive of CS1 outcomes. It establishes a practical, data-driven framework for timely identification of at-risk students and enables scalable, early interventions.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Web Mining and Content Analysis: Machine learning and data science for the Web
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Computer science's increased recognition as a prominent field of study has attracted students with diverse academic backgrounds. This has significantly increased the already high failure rates in introductory courses. To address this challenge, it is essential to identify struggling students early on. Incorporating in-class coding exercises in these courses not only offers additional practice opportunities to students but may also reveal their abilities and help teachers identify those in need of assistance. In this work, we seek to determine the extent to which the practice of using in-class coding exercises enhances the ability to predict student performance, especially early in the semester. Based on data obtained in a CS1 course taught at a mid-size American university, we found that in-class exercises could improve the prediction of students' eventual performance. In particular, we found relatively accurately predictions as early as academic weeks 3 through 5, making it possible to devise early intervention strategies. This work can benefit future studies on the impact of in-class exercises as well as intervention strategies throughout the semester.

Problem

• Predicting CS1 student performance using in-class coding exercises
• Identifying struggling students early through coding exercise analysis
• Enabling early intervention strategies with accurate performance prediction

Innovation

• Uses in-class coding exercises for prediction
• Predicts student performance from weeks 3-5
• Enables early intervention strategies for students