LOCAL GOVERNMENT UNIT 3: PUBLIC HEALTHCARE STOCK MANAGEMENT SYSTEM WITH FORECASTING ANALYTICS USING AI DRIVEN TREND ANALYSIS AND INSIGHTS

Abstract

This study presents the Public Healthcare Stock Management System with Forecasting Analytics using AI-Driven Trend Analysis and Insights, which addresses the recurring issue of supply mismatch in public healthcare stock facilities. The mismatch often results from continued reliance on manual and semi-automated inventory recording and monitoring methods. The proposed system serves as a centralized inventory hub for various public healthcare units, aiming to ensure efficient distribution and timely replenishment of medical supplies through an integrated request and tracking mechanism. The study employs the Agile Scrum methodology, which promotes iterative development and continuous user feedback. Development was carried out in sprint cycles, allowing incremental improvements and timely adjustments to system design. This approach ensured that the final system was user-friendly, robust, scalable, and capable of delivering practical forecasting analytics for informed inventory control. Moreover, the system was designed to integrate with external platforms used for stock requests and consumption, enabling seamless data exchange and enhancing overall visibility in inventory flow. The system implementation significantly reduced delays in stock requests and improved inventory tracking accuracy. The AI-driven forecasting component accurately predicted future demand based on historical data, allowing for proactive stock planning and minimizing the risk of shortages. The system's integrated design also enabled multiple healthcare units to coordinate stock requests more efficiently, reducing redundancy and miscommunication. The findings demonstrate the positive impact of intelligent stock management systems supported by agile development practices on public healthcare efficiency. By resolving supply mismatches and improving supply chain responsiveness, the system contributes to enhanced service delivery and a reduced risk of medical supply shortages. Future improvements may include expanding the forecasting model and incorporating real-time health indicators to further strengthen data-driven decision-making.