Predicting product demand is a critical challenge in retail and inventory management, as inaccurate forecasting often leads to overstocking, stockouts, and financial losses. This study presents a machine learning-based Inventory Demand Prediction System, titled INVEX, designed to forecast future product demand using historical sales data. The system leverages key features such as product category, selling price, stock levels, and past sales patterns to generate accurate demand predictions for retail businesses.

Two regression algorithms — Linear Regression and Random Forest Regressor — are implemented and compared to evaluate their effectiveness in predicting product demand. The dataset consists of structured sales records generated based on realistic retail scenarios, including daily transactions and product-level demand variations. The models are evaluated using standard performance metrics such as R² Score, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and overall prediction accuracy.Experimental results indicate that the Random Forest Regressor outperforms Linear Regression by effectively capturing non-linear demand patterns and seasonal variations in sales data. The system achieves a prediction accuracy of over 90%, demonstrating its capability to provide reliable and data-driven insights for inventory planning. The integration of a user-friendly interface enables store owners to manage products, generate bills, track sales history, and visualize predicted demand trends dynamically.

The proposed INVEX system offers a scalable and intelligent solution for modern retail environments by automating inventory decisions and reducing human dependency. It assists business owners in maintaining optimal stock levels, minimizing wastage, and improving profitability through accurate demand forecasting. This system can be extended further with real-time data integration and advanced machine learning models for enhanced predictive performance.

Keywords

 Machine Learning, Inventory Management, Demand Prediction, Linear Regression, Random Forest, Sales Forecasting, Retail Analytics, Data Analysis, Stock Optimization, Predictive Modeling, Business Intelligence, Inventory Optimization