Integrating predictive AI and Blockchain for student behavioral forecasting in higher education: A conceptual framework and multicase análisis
Integrating predictive AI and Blockchain for student behavioral forecasting in higher education: A conceptual framework and multicase análisis
-
DOI: https://doi.org/10.22533/at.ed.8208162614011
-
Palavras-chave: Algoritmos predictivos; tecnología blockchain; comportamiento del consumidor; universidades; inteligencia artificial; gestión institucional; transacciones.
-
Keywords: Predictive algorithms; blockchain technology; consumer behavior; universities; artificial intelligence; institutional management; transactions
-
Abstract: Universities need to anticipate students’ decisions (enrollment, switching, progression, dropout). Learning analytics and credential governance have been treated as separate domains. This creates a gap: AI generates insights, but a secure, auditable, institution-wide decision layer to operationalize them is missing. We pose three RQs: (how to combine academic, financial, and engagement data to predict behavior), (the role of blockchain in ensuring integrity, auditability, and governance), and (the organizational capabilities required to deploy an integrated analytics layer). We adopt a design-oriented, multi-case approach and propose the UCAS architecture, which integrates prediction with blockchain-based governance and credentials. We analyze six institutions using public documents and comparative thematic coding. Three findings emerge: first, predictive AI exists but in silos, without cross-unit orchestration; second, blockchain is used for credential issuance and verification, not as a governance layer for the behavioral data lifecycle; third, integration occurs when predictions are coupled to traceable operational triggers. Contribution: a model and roadmap to personalize services, improve retention, and align sustainability with privacy and traceability.
- Raul Jaime Maestre