2025 ASEE Annual Conference & Exposition

This paper presents the third-year results of the work supported by the National Science Foundation’s Revolutionizing Engineering Departments (IUSE/PFE: RED) Program under the project titled "IUSE/PFE:RED: Breaking Boundaries: An Organized Revolution for the Professional Formation of Electrical Engineers." The study looks at action-state orientation and its impacts on student success. The first-year results were presented at the 2023 ASEE Conference in Baltimore, MD with the academic paper titled "Predicting Academic Performance for Pre/Post-Intervention on Action-State Orientation Surveys" (Uysal, 2023). The objective of the first phase of the study was to find out how survey responses could be used to predict whether a student could be considered at-risk for failing academically. The second-year results were presented at the 2024 ASEE Conference in Portland, OR with the academic paper titled "Tracking and Predicting Student Performance Across Different Semesters with Matched Action-State Orientation Surveys and Interventions" (Uysal, 2024). The objective of the second phase of the study was to analyze and quantify the effects of in-class interventions on student study habits and, ultimately, their academic performance using action-state orientation surveys as engineering students progress further in their respective curriculum. The paper's major findings included high accuracy models in predicting student performance from action-state surveys and a quantifiable change in their survey responses after the interventions to improve their study habits.

In this paper, we explore the differences between higher GPA (3.5 or higher) and lower GPA (3.49 or lower) students when it comes to their study habits using the Shapley method which was originally derived from cooperative game theory to fairly distribute the total gains (or costs) among participants based on their individual contributions. This method is now widely applied in machine learning interpretability to attribute the importance of each feature in a model’s prediction, commonly referred to as explainable AI or XAI. The Shapley method will be applied to GPA predictive algorithms trained on both high and low GPA datasets to identify the features (in this case, the action-state survey responses to individual questions) that contribute the most to a student's academic outcome in a comparative framework to study the differences in the importance of study habits in contributing to their academic performance. Our hypothesis is that the feature rankings of high and low GPA students will be different to provide actionable information on which study habits should be stressed more for realizing higher academic potential in struggling students.