IoT-Based Smart Pharmacies for Optimizing Stock Management with Long Short-Term Memory Model

• Main Authors: A, Karthiayani, Raman, Ramakrishnan
• Format: Conference Proceeding
• Language: English
• Subjects: Customer satisfaction; Data models; Decision making; Demand forecasting; Internet of Things; Inventory optimization; Medical services; Operational efficiency; Predictive analytics; Predictive models; Real-time data; Real-time systems
• ISSN: 2769-2884
• DOI: 10.1109/ICRITO61523.2024.10522450

This research presents a new method for optimizing pharmaceutical inventory management using a combination of Long Short-Term Memory (LSTM) and Internet of Things (IoT) technologies. Problems with overstocking or stockouts, caused by inefficient traditional methods of stock management, may drive up expenses and leave customers unhappy. It provides a method that makes use of IoT devices to track inventory levels, sales trends, and other pertinent metrics in real-time. After that, the LSTM model is used to examine the data and make accurate predictions about stock needs in the future. The LSTM model allows for proactive stock replenishment decision-making by continually learning from previous data, thereby adapting to shifting demand patterns. It shows that our suggested approach optimizes stock levels, reduces inventory holding costs, and improves customer satisfaction via simulated studies and real-world deployments. Modern pharmacies may improve their operational efficiency and stock management procedures by integrating the IoT with LSTM. This approach is both scalable and efficient.