An Integrated Data Analytic Approach for Achieving Operational Excellence in Supply Chain

Supply chains are quiet complex structures consisting of suppliers, manufacturers, distributors, retailers, and consumers themselves. Accordingly, this raises many issues like delays in production, logistical bottlenecks, thus causing overstock or stockouts. In order to ensure that it functions efficiently and adapt to changes in demand, supply disruptions, and other uncertainties, our study utilizes a data analytics-based approach to achieve operational excellence in a simulation environment that spans over 1-year time horizon. The proposed approach involves predicting demands using the XGBoost technique, managing inventory dynamically under stochastic demand and lead times by calculating safety stocks, reorder points, and predicting lead times through linear regression. The effectiveness of these strategies is evaluated by visualizing key performance metrics such as inventory turnover, service level, and the order fulfillment rate for each product considered in simulation process. Through this study, we aim to enhance decision-making processes in real-life supply chain management, for ensuring that enterprises maintain high service levels and meet customer demands effectively in a rapidly evolving dynamic market environment. The study also highlights on some potential research extensions as well.