Demand Forecasting for Perishable Goods in Retail Using Big Data Analytics

Abstract

This research tackles the challenge of perishable food product management in grocery stores through Big Data Analytics. It employs the Moving Average algorithm and Linear Regression for sales trend prediction and inventory optimization, implemented using Python. The Moving Average algorithm smoothens sales data fluctuations, aiding trend identification, while Linear Regression predicts future sales patterns based on historical data. A sample dataset with daily sales is used to demonstrate the techniques, visually presenting actual sales data alongside Moving Average and Linear Regression forecasts. The study aims to enhance forecasting accuracy, minimize waste, and improve inventory management efficiency in grocery stores. By harnessing Big Data Analytics, it offers insights for optimizing perishable goods supply chain operations, presenting a practical, data - driven approach for the retail sector. The forecasting models' flexibility and adaptability to diverse datasets hold promise for revolutionizing perishable food product management in retail.