Article’s

Modern supply chains generate large volumes of operational data related to inventory levels, supplier performance, shipping costs, lead times, and product quality. Managing these factors efficiently is essential for ensuring smooth business operations and reducing supply chain disruptions. This research presents a Data Science Driven Prescriptive Analysis System for Smart Supply Chain Management that combines machine learning techniques with real-time monitoring and decision-support capabilities. The proposed system utilizes data preprocessing, feature analysis, and predictive modeling using Linear Regression and Random Forest Regressor algorithms to analyze supply chain performance and identify potential risks. The dataset is divided into training and testing sets to evaluate model effectiveness using standard performance metrics. In addition to predictive analytics, the system incorporates real-time risk detection, supplier intelligence scoring, alert generation, and prescriptive recommendations to support proactive decision-making. An interactive dashboard developed using modern web technologies provides visual insights into inventory trends, supplier performance, and operational risks. Experimental results indicate that the Random Forest Regressor outperforms traditional regression approaches in predicting supply chain outcomes and risk patterns. The proposed solution enhances supply chain visibility, improves operational efficiency, minimizes disruptions, and enables organizations to make informed and data-driven strategic decisions.