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{207263,
        author = {Penmetsa Likhita Naga Sai and Dr.Uma Sharma},
        title = {Artificial Intelligence-Based Predictive Analytics to improve operational resilience in Retail and E-Commerce Supply Chain: A Demand Forecasting and Inventory Disruption Management Focus.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {323-340},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207263},
        abstract = {Purpose The retail and e-commerce supply chains are under pressure with growing uncertainty in the demand, interruptions and consumer behaviour changing quickly. More conservative forecasting and inventory methods are not very effective in such dynamic settings and result in inefficiencies such as stockouts, surplus inventory and low service levels. This paper will look at the benefits of using AI-powered predictive analytics to improve operational resilience, especially in the field of refining demand forecasts and inventory disruptions.
Literature Review and Gaps in the research
Available literature demonstrates that predictive analytics and artificial intelligence enhance the accuracy of forecasts and efficiency of the supply chain. Nevertheless, the bulk of the studies have a general approach and lack the specificity of the retail and e-commerce context. Moreover, a scarcity of research offers a combined perspective between predicting, inventory, and operational resilience. This paper fills in these blank spaces by providing a more specific and combined approach.
Methodology
The research takes a descriptive research design based on secondary data of selected studies. The demand volatility, accuracy of prediction, optimization of inventory and disruption management are the main themes that are determined through a qualitative thematic analysis.  
Analysis & Findings
The findings reveal that the conventional forecasting models are unable to cope with the dynamic demand trends and can cause inefficiencies. Predictive analytics powered by AI enhances accuracy because it combines real-time and multi-source data, making it possible to make adaptive predictions of demand. This will aid in improved inventory management, such as ideal stock quantity and effective replenishment. It also allows timely identification of disruptions, facilitates proactive decision-making and enhances supply chain responsiveness.
Conclusion: Predictive analytics powered by AI is essential in improving operational resilience within e-commerce and retail supply chains. It facilitates the making of sound decisions in a shaky environment by enhancing accuracy in forecasting, efficiency in inventory management, and proactive risk mitigation. Another contribution of the study is that it provides a conceptual framework that incorporates forecasting, inventory optimization and disruption management into a single and flexible system.},
        keywords = {Artificial Intelligence, Predictive Analytics, Demand Forecasting, Inventory Optimization, Supply Chain Resilience},
        month = {August},
        }