skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A Mixture of Experts in Forecasting Student Performance in Classroom Programming Activities
Predicting students' performance early in programming courses is crucial because it allows instructors to intervene early, improving learning outcomes. Currently, no existing platforms can effectively forecast student performance in programming activities based on students' developed code. Forecasting student scores based on their programming activities is challenging because the accuracy of different predictive models often varies throughout these activities. To address this challenge, we introduce a novel framework utilizing Mixture of Experts (MoE). The MoE method combines insights from various neural networks and dynamically picks the most accurate predictions. This system significantly enhances the reliability of forecasting each student's performance within the first 15 minutes of a 30-minute programming session. By enabling early predictions, the MoE provides instructors with a powerful mechanism to understand and support the student learning process in real-time.  more » « less
Award ID(s):
2215849
PAR ID:
10593044
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
ACM
Date Published:
ISBN:
9798400704369
Page Range / eLocation ID:
4000 to 4004
Format(s):
Medium: X
Location:
Boise ID USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Journal of Educational Data Mining)
    The ability to predict student performance in introductory programming courses is important to help struggling students and enhance their persistence. However, for this prediction to be impactful, it is crucial that it remains transparent and accessible for both instructors and students, ensuring effective utilization of the predicted results. Machine learning models with explainable features provide an effective means for students and instructors to comprehend students' diverse programming behaviors and problem-solving strategies, elucidating the factors contributing to both successful and suboptimal performance. This study develops an explainable model that predicts student performance based on programming assignment submission information in different stages of the course to enable early explainable predictions. We extract data-driven features from student programming submissions and utilize a stacked ensemble model for predicting final exam grades. The experimental results suggest that our model successfully predicts student performance based on their programming submissions earlier in the semester. Employing SHAP, a game-theory-based framework, we explain the model's predictions, aiding stakeholders in understanding the influence of diverse programming behaviors on students' success. Additionally, we analyze crucial features, employing a mix of descriptive statistics and mixture models to identify distinct student profiles based on their problem-solving patterns, enhancing overall explainability. Furthermore, we dive deeper and analyze the profiles using different programming patterns of the students to elucidate the characteristics of different students where SHAP explanations are not comprehensible. Our explainable early prediction model elucidates common problem-solving patterns in students relative to their expertise, facilitating effective intervention and adaptive support. 
    more » « less
  2. ; ; (, Explaining Explainability: Early Performance Prediction with Student Programming Pattern Profiling)
    The ability to predict student performance in introductory programming courses is important to help struggling students and enhance their persistence. However, for this prediction to be impactful, it is crucial that it remains transparent and accessible for both instructors and students, ensuring effective utilization of the predicted results. Machine learning models with explainable features provide an effective means for students and instructors to comprehend students' diverse programming behaviors and problem-solving strategies, elucidating the factors contributing to both successful and suboptimal performance. This study develops an explainable model that predicts student performance based on programming assignment submission information in different stages of the course to enable early explainable predictions. We extract data-driven features from student programming submissions and utilize a stacked ensemble model for predicting final exam grades. The experimental results suggest that our model successfully predicts student performance based on their programming submissions earlier in the semester. Employing SHAP, a game-theory-based framework, we explain the model's predictions, aiding stakeholders in understanding the influence of diverse programming behaviors on students' success. Additionally, we analyze crucial features, employing a mix of descriptive statistics and mixture models to identify distinct student profiles based on their problem-solving patterns, enhancing overall explainability. Furthermore, we dive deeper and analyze the profiles using different programming patterns of the students to elucidate the characteristics of different students where SHAP explanations are not comprehensible. Our explainable early prediction model elucidates common problem-solving patterns in students relative to their expertise, facilitating effective intervention and adaptive support. 
    more » « less
  3. ; ; (, Educational Data Mining)
    The ability to predict student performance in introductory programming courses is important to help struggling students and enhance their persistence. However, for this prediction to be impactful, it is crucial that it remains transparent and accessible for both instructors and students, ensuring effective utilization of the predicted results. Machine learning models with explainable features provide an effective means for students and instructors to comprehend students' diverse programming behaviors and problem-solving strategies, elucidating the factors contributing to both successful and suboptimal performance. This study develops an explainable model that predicts student performance based on programming assignment submission information in different stages of the course to enable early explainable predictions. We extract data-driven features from student programming submissions and utilize a stacked ensemble model for predicting final exam grades. The experimental results suggest that our model successfully predicts student performance based on their programming submissions earlier in the semester. Employing SHAP, a game-theory-based framework, we explain the model's predictions, aiding stakeholders in understanding the influence of diverse programming behaviors on students' success. Additionally, we analyze crucial features, employing a mix of descriptive statistics and mixture models to identify distinct student profiles based on their problem-solving patterns, enhancing overall explainability. Furthermore, we dive deeper and analyze the profiles using different programming patterns of the students to elucidate the characteristics of different students where SHAP explanations are not comprehensible. Our explainable early prediction model elucidates common problem-solving patterns in students relative to their expertise, facilitating effective intervention and adaptive support. 
    more » « less
  4. ; ; (, the 16th International Conference on Educational Data Mining (EDM 2023))
    Prediction of student performance in Introductory programming courses can assist struggling students and improve their persistence. On the other hand, it is important for the prediction to be transparent for the instructor and students to effectively utilize the results of this prediction. Explainable Machine Learning models can effectively help students and instructors gain insights into students’ different programming behaviors and problem-solving strategies that can lead to good or poor performance. This study develops an explainable model that predicts students’ performance based on programming assignment submission information. We extract different data-driven features from students’ programming submissions and employ a stacked ensemble model to predict students’ final exam grades. We use SHAP, a game-theory-based framework, to explain the model’s predictions to help the stakeholders understand the impact of different programming behaviors on students’ success. Moreover, we analyze the impact of important features and utilize a combination of descriptive statistics and mixture models to identify different profiles of students based on their problem-solving patterns to bolster explainability. The experimental results suggest that our model significantly outperforms other Machine Learning models, including KNN, SVM, XGBoost, Bagging, Boosting, and Linear regression. Our explainable and transparent model can help explain students’ common problem-solving patterns in relationship with their level of expertise resulting in effective intervention and adaptive support to students. 
    more » « less
  5. ; ; ; (, ITiCSE '19: Proceedings of the 2019 ACM Conference on Innovation and Technology in Computer Science Education)
    Learning programming in early introductory classes is challenging for first year university students, and introducing parallel programming (PDC) in early classes along with traditional sequential programming is even more challenging. Unplugged activities may help alleviate some of the difficulties for students. Unplugged activities have been shown to increase student interest, and to enhance student understanding of CS programming concepts. We have used unplugged activities to teach PDC concepts before introducing parallel programming. Our experiences show that using unplugged activities to introduce the PDC concepts reduce the barrier to learn parallel programming. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email