I-Corps: Translation Potential of an Artificial Intelligence (AI)-Driven Educational Platform for High School Math Instructors

This I-Corps project is based on the development of an educational software platform for high school math instructors and students. Learning disparities in high school math education are caused by various factors including varying levels of prior knowledge and learning needs and limited availability for personalized support. These factors together contribute to significant barriers in learning math for many students, impacting their college academic paths and their success in Science, Technology, Engineering and Mathematics (STEM)-related fields. This technology addresses these issues by providing an artificial intelligence (AI)-driven, interactive visual learning software platform to support instructors in detecting potential learning gaps. Currently, instructors rely mainly on static instructional methods that do not adapt well to students’ personalized learning needs. In addition, these static methods pose challenges for instructors to detect students’ learning disparities and in identifying the causative factors associated with these disparities. This technology platform can dynamically analyze students’ learning performance while generating clear, contextualized, and actionable insights for instructors. By integrating advanced technologies into real educational practices, this technology may benefit math education student outcomes. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of an artificial intelligence (AI)-driven educational software platform to support high school math instructors. This technology is an adaptive platform that integrates large language models (LLMs), data analysis, and interactive data visualization techniques. The goal is to enable instructors to identify students’ learning disparities, analyze the influential factors, evaluate algorithmic accountability, and implement effective strategies to close the performance gaps. The process used is guided by a framework derived from Bloom’s Taxonomy for aligning the analytical process with educational methodologies to enhance educational outcomes. The solution leverages LLMs to interpret the analytical results within real math learning contexts, ensuring generated insights are understandable, trustworthy, and actionable for educators. In addition, the platform offers contextualized explanations about learning disparities for educators, enabling them to make informed, data-driven decisions while enhancing their confidence in engaging with AI. For students, this platform may transform the passive math learning process into interactive, adaptive, and data-driven experiences. For teachers, the platform’s contextualized interpretations may demystify the instruction and learning process, supporting targeted and effective teaching practices. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.