Excellence in Research: Artificial Intelligence-Driven Learning Analytics to Predict Student Performance in STEM Education at Historically Black Colleges and Universities

About This Grant

This project will support the national interest by promoting broadly accessible engineering education through the integration of artificial intelligence (AI) and learning analytics at Historically Black Colleges and Universities (HBCUs). The project plans to enhance student engagement, improve academic performance, and increase retention in STEM fields by delivering personalized, real-time feedback to both students and faculty. By tapping into the strengths and potential of students, the initiative will foster a data-informed, student-centered learning environment that is adaptable and scalable across engineering courses. The significance of this work lies in its potential to improve educational outcomes and close achievement gaps in STEM disciplines, contributing to the advancement of a highly skilled engineering workforce. This project aims to strengthen research capacity at an HBCU through empowering faculty and students in the adoption of emerging technologies. The broader impact of this work lies in its potential to transform STEM learning environments nationwide and establish a scalable, evidence-based model for advancing educational innovation. Technically, the goals of the project are to integrate AI-driven performance prediction models with real-time learning analytics to support collaborative learning in undergraduate engineering courses. The scope of the research includes designing, training, and validating predictive models using machine learning techniques. These models will draw on a range of data inputs, including demographic information, academic history, financial aid status, and indicators of student engagement to generate timely, actionable feedback for instructors and students. A quasi-experimental design will be used to assess the impact of the intervention by comparing learning outcomes in courses implementing the AI-enhanced system against those using traditional instruction. The project also includes structured faculty development, ongoing formative and summative evaluation, and dissemination of results through scholarly publications and national conferences. The expected outcomes include actionable strategies for using AI to support students in STEM and evidence-based recommendations for broadening participation in engineering education. 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.