Predictive Disruption Management in CPG(Consumer Packaged Goods) Supply Chains Using AI and IoT Integration

Modern supply chains, especially Consumer Packaged Goods (CPG) supply chains, are prone to disruptions due to delays, varying demand, and climate change. Pre-determined plan-based conventional logistics models are likely to be unable to predict such disruptions. This tends to result in operational inefficiencies and inventory inaccuracies. Current research suggests a cost-effective, real-time model that combines Artificial Intelligence (AI) and Internet of Things (IoT) technologies to predict disruptions and improve operational efficiency. The system utilizes RFID and GPS-enabled edge sensing, as well as external APIs for weather and demand. The system utilizes machine learning algorithms such as Naïve Bayes for disruption classification and Long Short-Term Memory (LSTM) networks for delay forecasting. After rigorous testing through simulations and field trials using ESP32 microcontrollers, the model achieved a classification accuracy of 91% and a 26% reduction in the root mean square error (RMSE) of delay forecasts. When applied across logistics nodes, it provided greater operational visibility, reduced stockouts, and ensured hassle-free hardware-software integration. The method provides an extensible solution for smart supply chain management. The dashboard implemented using Streamlit also supports real-time monitoring and decisionmaking, and its modular structure supports applicability across industries such as fast-moving consumer goods (FMCG), retail, and healthcare.