PREDICTION OF BIG MART SALES BY USING MACHINE LEARNING

Abstract

In today’s competitive retail industry, accurate sales prediction plays a crucial role in inventory management, demand forecasting, and business decision-making. Big Mart, a retail chain with multiple outlets, generates large volumes of sales data that can be effectively analyzed using machine learning techniques. This project aims to predict product sales at various Big Mart outlets by leveraging historical sales data and applying advanced machine learning algorithms. The dataset includes features such as item type, outlet size, location, visibility, and pricing. Data preprocessing techniques such as handling missing values, encoding categorical variables, and normalization are applied to improve model performance. Various regression algorithms such as Linear Regression, Decision Tree, Random Forest, and XGBoost are implemented and compared. Experimental results show that ensemble methods like Random Forest and XGBoost outperform traditional models in terms of prediction accuracy and error minimization. The system is implemented using Python in Jupyter Notebook for training and Flask for deployment, enabling real-time sales prediction. The proposed system helps retailers optimize stock management, reduce losses, and improve profitability.