Zero-Waste Inventory Management Using Predictive and Prescriptive Analytics for Perishable Goods in Retail

Abstract

Inventory management is crucial for retail businesses, especially for perishable products where overstock leads to waste, and understock risks missed sales. This thesis presents a framework for Zero-Waste Inventory Management using predictive and prescriptive analytics. Predictive analytics is used to forecast demand based on historical sales and contextual factors, while prescriptive analytics recommends optimized stocking levels that minimize waste and maximize customer satisfaction. The framework combines machine learning and linear programming to achieve optimal inventory levels, enhancing sustainability and profitability in grocery retail.