Recent Papers

This research paper presents the results of predicting Big Mart product sales using machine learning algorithms. The objective of this work is to build a model that accurately estimates sales across different outlets based on product and store-related attributes such as Item Weight, Item Visibility, Item MRP, Outlet Size, Outlet Location, and Outlet Type. Accurate sales prediction is essential for inventory management, demand forecasting, pricing strategies, and business decision-making for retail companies. Unlike traditional forecasting methods, which often fail to capture complex relationships and multiple influencing factors, this approach leverages machine learning to deliver better accuracy and interpretability. In this work, Linear Regression and Ensemble Models are employed to establish relationships between independent variables (predictors) and the dependent variable (sales).The methodology includes dataset loading, data preprocessing, categorical encoding, exploratory data analysis, feature selection, and splitting the dataset into training and testing sets. The models are trained to minimize prediction errors and capture meaningful sales patterns across products and outlets. Evaluation of model performance is carried out using metrics such as R Score, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) to ensure robustness and reliability.This approach provides insights into how key factorssuch as product pricing, visibility, and outlet characteristicsaffect sales, helping retailers optimize supply chain planning and enhance customer satisfaction. By implementing a scalable and interpretable machine learning model, this study demonstrates the applicability of data-driven techniques for predictive analytics in the retail domain.Keywords: Big Mart, Sales Prediction, Machine Learning, Linear Regression, Ensemble Models, Supervised Learning

Copyright © 2025 Miryala Rakesh. This is an open access article distributed under the Creative Commons Attribution License.