Student Persistence as Academic Intelligence: An Integrationist Learning Analytics Framework for Higher Education

Abstract

Student persistence remains a major challenge in higher education worldwide, particularly in contexts marked by expansion, diversification, and persistent inequalities. Although previous research has generated important insights into student engagement, integration, and retention, many approaches remain limited in their ability to account for the systemic, dynamic, and data-rich conditions that shape contemporary higher education.

This article proposes a theoretical-methodological framework that reconceptualizes student persistence as a form of institutional intelligence. Grounded in the MIPESA model, which understands persistence as an emergent outcome of interactions among institutional management, course quality, teaching practice, and student engagement, the study proposes an integrative architecture that connects theory, analytics, and institutional action.

More specifically, the article introduces the Student Persistence Index (IPE-PESA), a multidimensional analytical model designed to support the early identification of students at risk through the integration of academic, behavioral, and contextual data. It also develops the concept of Academic Persistence Intelligence (API), through which predictive analytics, institutional interventions, and continuous evaluation are linked within a systemic decision-making framework. In addition, the study incorporates a territorial dimension through Atlas PESA, enabling the identification of spatial patterns of student vulnerability and supporting context-sensitive institutional responses. 

By integrating educational theory, learning analytics, and institutional strategy, the article contributes to current debates on student persistence and student success by offering a scalable and conceptually grounded framework for proactive.