Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175745,
        author = {Litisha Miraclin},
        title = {Wide Range Retail Sales Prediction Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3703-3712},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175745},
        abstract = {The use of machine learning predicts future sales by training a model using previous sales data. The overview for sales projection in machine learning highlights the use of several machine learning methods to forecast sales. The approach includes processes such as data collection and the preprocessing process feature selection, and training models. Different metrics are employed to evaluate the model's accuracy and effectiveness. The study's purpose is to give details about the greatest algorithms for machine learning for forecasting sales and how they may be applied in various organizations. The above report assesses the efficacy of predictive machine learning models in predicting sales across sectors. The study examines past sales data and evaluates the efficacy of several machine learning methods, including. Logistics Regression, and XGBoost Regressor in forecasting earnings in the future. Businesses can use this method to make the most of the assets they have and boost profits. Currently, as the sum of information available grows dramatically, organizations are focusing towards the rational application of massive amounts of information to help predict the next generation and arrive at better choices. In the past few decades, investigators and companies have grown more interested in applying predictive machine learning algorithms for predicting brand and commodity sales. This work presents the XGBoost sale forecasting method, and this includes an algorithm called XGBoost with painstaking design of features treatment to anticipate the sales problem. The strategy presented in this study successfully mines qualities from various perspectives in order to create accurate forecasts. This study assesses their XGBoost revenue forecasting algorithm using data on sales from stores obtained through the Kaggle challenge. Experimental findings reveal that this approach outperforms the other training methodologies.},
        keywords = {machine Learning, Sales Prediction, XG-Boost Regression},
        month = {April},
        }