A Predictive Analysis for Big Mart Sales Using Machine Learning Algorithm

G. Vamsi 1, K. Venu Prasad 2

1 Assistant Professor,  2 MCA Final Semester, Master of Computer Applications, Sanketika Vidya Parishad Engineering College, Vishakhapatnam, Andhra Pradesh, India

Gvkrishna2002@gmail.com, venuprasadkhamitkar @gmail.com

Abstract: The Predictive Analysis for Big Mart Sales Using Machine Learning Algorithm project aims to predict product sales using historical sales data and machine learning techniques. The system analyzes various factors such as product type, outlet size, outlet location, item visibility, and product price to estimate future sales accurately. Data preprocessing techniques, including missing value handling and categorical encoding, are applied to improve data quality. Machine learning algorithms such as Linear Regression, Decision Tree, Random Forest, and XGBoost are trained and evaluated to identify the best-performing model. The selected model is deployed through a Flask web application, allowing users to enter product details and obtain sales predictions instantly. This system helps retailers improve inventory management, reduce stock shortages, minimize losses, and make better business decisions. Overall, the project demonstrates that machine learning provides an effective and reliable solution for retail sales forecasting.

Keywords: Machine Learning, Big Mart Sales Prediction, Sales Forecasting, Data Preprocessing, Feature Engineering, Linear Regression, Decision Tree, Random Forest, XGBoost, Flask, Predictive Analytics, Regression Models, Inventory Management, Retail Analytics, MAE, MSE, R-Squared (R²).