Enhancing Student Success through GAI and Predictive Analytics

Abstract

Generative artificial intelligence and predictive analytics are increasingly integrated into digital learning environments, yet most institutional implementations treat these technologies as parallel tools rather than components of a unified, closed-loop support system. This conceptual paper proposes a theoretically grounded 16-stage framework that systematizes the integration of Generative artificial intelligence and predictive analytics to enhance learner support, instructional decision-making, and institutional responsiveness in online higher education. Drawing on systems theory and the learning analytics cycle, the framework illustrates how data ingestion, predictive modeling, generative feedback, and educator judgment can function together as an adaptive socio-technical ecosystem. Two guiding questions inform the analysis: (1) How can predictive and generative AI be combined to provide timely, personalized, and scalable support for diverse learners? and (2) What institutional, pedagogical, and ethical conditions are required for responsible implementation? By synthesizing current research and identifying gaps in existing approaches, this paper outlines practical considerations for adoption and highlights implications for governance, faculty development, and equitable system design. The proposed model serves as a foundational structure for institutions seeking to align emerging AI technologies with human-centered teaching and learning.