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{188844,
        author = {Prasad Rajendra Kolte and Shreya Shrimant Raghoji and Mayur Keshav Pawar and Sagar Satish Zujam},
        title = {SmartShelf: AI-Powered Unsold Inventory Management with Geotagged Demand and Flash Sale Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3522-3525},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188844},
        abstract = {Efficient inventory management is essential for maintaining profitability in retail and supply chain operations. Unsold or slow-moving products increase storage costs, block working capital, and reduce revenue. This paper presents SmartShelf, an AI-powered Unsold Inventory Management System that identifies stagnant inventory, forecasts demand using geotagged sales data, and generates region-specific flash-sale recommendations to optimize stock movement. SmartShelf integrates machine learning models (XGBoost for demand forecasting, SVM for inventory classification, and Linear Regression for interpretability) with a vendor-facing dashboard and an API bridge to an AI core. Experimental results on prototype datasets demonstrate improved inventory turnover and practical benefits for small and medium enterprises (SMEs).},
        keywords = {AI in Retail, Inventory Optimization, Unsold Inventory Management, Demand Forecasting, Geotagged Data Analytics, Flash Sale Automation.},
        month = {December},
        }