2026 ASEE Annual Conference & Exposition

This study investigates the effectiveness of Generative AI, specifically ChatGPT’s Study and Learning mode, in supporting engineering students without prior Linear Algebra coursework as they learn Linear Programming (LP) modeling in a supply chain modeling course. LP formulation is a fundamental skill in optimization, yet many students enter the course with uneven mathematical backgrounds, creating knowledge gaps that may hinder students’ achievement of learning outcomes. To address this challenge, the research evaluates whether ChatGPT can help bridge the knowledge gap by providing personalized guidance and explanations in addition to traditional classroom instruction. The methodology involves collecting student background data on Linear Algebra competency before taking the course and comparing performance on LP-related homework and exams between two groups after having AI assistance: students with a Linear Algebra background and those without. The anticipated findings demonstrate whether the integration of ChatGPT helps narrow existing performance gaps between the two groups and seek to determine the degree to which the tool contributes to reducing these disparities. By quantifying differences between the two groups in exam and homework grades before and after introducing the use of GhatGPT’s Study and Learning mode, the study aims to assess ChatGPT’s role as an effective learning support tool for students with limited mathematical backgrounds in engineering courses. The results are expected to inform educators on the potential of Generative AI to supplement traditional instruction, particularly in identifying and filling foundational knowledge gaps.