Copyright © 2026 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{194833,
        author = {THALETI POTHURAJU MEGHANA SAI and Yeturu Aasritha Reddy and Tunga Mounika Lakshmi and Raavi Hindu and Mr. Raghavendran N},
        title = {Machine Learning-Driven Predictive Analytics for Retail Sales Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6180-6190},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194833},
        abstract = {The rapid growth of e-commerce and retail industries has generated vast amounts of transactional data, creating both the opportunity and necessity for intelligent data-driven decision-making. This paper presents ShopPulse, an AI-powered retail management system that integrates predictive analytics, machine learning, and real-time data processing to forecast sales, optimize inventory, and maximize revenue. The system leverages XGBoost for hourly sales forecasting, Facebook Prophet for 30-day demand prediction, Random Forest for inventory risk classification, and Gradient Boosting for dynamic price optimization across product categories. A dataset of 54,000+ hourly retail transactions spanning multiple stores, regions, and product categories forms the foundation of model training. The system is deployed as a full-stack web application using Flask, SQLite, and interactive HTML5 dashboards powered by Chart.js. SHAP (SHapley Additive explanations) is employed for explainable AI, enabling stakeholders to understand feature contributions to predictions. Experimental results demonstrate strong predictive accuracy, with the XGBoost model achieving high R-squared scores and low Mean Absolute Error across test splits. The proposed system addresses critical retail challenges including stockouts, pricing inefficiencies, and revenue forecasting uncertainties, offering a scalable, interpretable, and deployable solution for modern retail enterprises.},
        keywords = {Sales Prediction, XGBoost, Facebook Prophet, Random Forest, SHAP, Flask, Retail Analytics, Inventory Management, Dynamic Pricing, Machine Learning.},
        month = {March},
        }