AI & Data-Driven Inventory Management for Improving Medicine Availability at Jan Aushadhi Kendras

Abstract

Abstract: The rapid expansion of the Pradhan Mantri Bhartiya Janaushadhi Pariyojana (PMBJP) has significantly enhanced access to affordable generic medicines across India through a growing network of Jan Aushadhi Kendras (JAKs). However, the long-term success of this network relies heavily on consistent medicine availability. Operational challenges—such as localized stockouts, inventory imbalances, and expiry-related wastage—disrupt supply chains and threaten patient access to affordable healthcare. This highlights a critical need to examine how emerging tools like Artificial Intelligence (AI) and predictive data analytics can optimize inventory management within the PMBJP framework. The purpose of this study is to examine the potential of AI-based demand forecasting and data-driven inventory models to maximize medicine availability and improve asset turnover at JAKs. The study adopts a descriptive and analytical research design based on secondary data sourced from PMBI and PIB publications, government reports, and peer-reviewed literature on AI applications in pharmaceutical logistics. Trend analysis, comparative evaluations, and qualitative synthesis are utilized to assess PMBJP’s unique operating environment against empirical evidence from comparable health systems. Findings from parallel healthcare settings show that AI-enabled inventory systems can reduce stockouts by 30–55%, increase inventory turnover by up to 70%, and cut expired inventory losses by 20–33%. While these figures do not represent direct empirical data from individual JAK outlets, they provide robust conceptual support for AI integration. Crucially, the study identifies PMBI’s existing IT-enabled supply chain infrastructure and digital ecosystem as an ideal, mature foundation to host these future AI applications. Future research should focus on developing and testing JAK-specific AI models using store-level sales, inventory, and localized demand data. Implementing such automated decision-support models could systematically eliminate stockouts, curb chemical wastage, and strengthen overall supply chain resilience. Ultimately, this technological transition supports more reliable public access to affordable medicines, contributing directly to a highly inclusive and sustainable public healthcare system. Keywords: Jan Aushadhi Kendras, AI, inventory management, medicine availability, stockouts, PMBJP