E-Commerce Product Demand Prediction System: Using Statistical Forecasting Techniques

The rapid growth of e-commerce platforms has generated large volumes of digital sales data. This paper proposes an E-Commerce Product Demand Prediction (EPDP) system that automates demand forecasting using statistical methods such as Moving Average and Linear Regression. The system integrates sales management, inventory monitoring, and demand prediction within a web-based platform. Experimental results demonstrate improved decision making for inventory planning in small and medium-scale e- commerce businesses. The demand forecasting module utilizes statistical techniques such as Moving Average and Linear Regression to analyze the previous twelve months of sales data and estimate future product demand. Each prediction is accompanied by a confidence score that reflects the reliability of the forecast.