<![CDATA[This study aims to address the computational limitations of traditional on-premise servers in higher education by proposing an integrated cloud-based big data analytics framework tailored for Learning Management Systems (LMS). Through a literature-based case study methodology, recent peer-reviewed studies from major academic databases were systematically extracted, compared, and synthesized to identify infrastructural gaps and design a novel conceptual model. The results indicate that while existing analytical models achieve high predictive accuracy, they frequently fail at the institutional scale due to latency bottlenecks and limited pedagogical usability. To resolve these issues, this study formulates a three-layered architecture comprising a Data Ingestion Layer, a Cloud Analytics Engine Layer, and a Decision Support System (DSS) Presentation Layer. This framework efficiently offloads heavy computational workloads to scalable cloud environments and translates complex algorithmic outputs into actionable insights via an intuitive academic dashboard. Implementation scenarios, such as student early warning systems and curriculum difficulty evaluations, demonstrate the framework's practical utility over traditional approaches. In conclusion, the proposed architecture effectively transforms static LMS platforms into proactive DSS. Future research should prioritize empirical prototyping with real-time institutional data and the integration of advanced security encryption protocols to ensure compliance with educational data privacy regulations.]]>
Copyrights © 2025
