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{187754,
        author = {Yugandhar Shilawane},
        title = {AI-ENHANCED DIGITAL TWINS FOR OPTIMIZING VIRTUAL BUSINESS OPERATIONS IN SUPPLY CHAINS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {6058-6098},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187754},
        abstract = {The results extend the knowledge of how AI-aided demand forecasting and digital twin concepts can be used to generate insights into inventory management and supply chain decisions. In this case, through the comparison of the specific characteristics of the implemented models, the research focuses on the advantage of XGBoost in terms of model complexity, computation time, and prediction performance. 
Some of the limitations cone with this study involve issues to do with data limitation and also the issue of data destiny in some models that take a long to produce results. To effectively apply AI for predicting building failure, there is a need for the following recommendations in the subsequent research; The quality of data must be improved since better data provide better results. These findings correspond with the purpose of this study and offer practical recommendations for supply chain practitioners regarding demand planning enhancement.},
        keywords = {Demand Forecasting, Supply Chain Optimization., AI-Enhanced Digital Twin, Machine Learning Models, XGBoost, Feature Engineering, Inventory Management Time, Series Analysis, Seasonality and Trends, Mean Absolute Error (MAE)},
        month = {November},
        }