<![CDATA[This study proposes and evaluates an intelligence-oriented hybrid information system architecture for pharmaceutical data analytics and decision support. Unlike conventional approaches that treat analytics as an external component, the proposed framework embeds analytical intelligence directly into the core system architecture through an integrated, multi-layer design. The study adopts an experimental and system development methodology using a large-scale public pharmaceutical dataset consisting of 240,591 records and 10 attributes. Supervised machine learning models are implemented to support data classification and intelligence generation, and system performance is evaluated using accuracy, precision, recall, and F1-score. The results demonstrate that the proposed hybrid system consistently outperforms baseline and non-integrated approaches, achieving higher predictive stability and analytical consistency. The main contribution of this study lies in its system-level integration model, which enables the transformation of raw pharmaceutical data into actionable decision-support intelligence. The findings confirm that embedding analytics within information system architecture significantly enhances both analytical performance and decision-making capability in pharmaceutical information systems.]]>
Copyrights © 2026
