Abstract: Modern supply chains operate under persistent volatility, where disruptions driven by geopolitical instability, logistics bottlenecks, and environmental events routinely challenge operational continuity. This paper examines how the integration of Artificial Intelligence (AI) capabilities within Enterprise Resource Planning (ERP) systems enables technically agile and resilient supply chain operations. The study focuses on AI-driven functionalities embedded in ERP architectures, including machine learning–based demand forecasting, anomaly detection, and predictive maintenance, and evaluates their impact on real-time decision-making under uncertainty. Using a combination of system-level modeling, algorithmic performance analysis, and simulation of disruption scenarios, the research assesses improvements in data interoperability, latency reduction, and adaptive resource reconfiguration enabled by AI-enhanced ERP environments. The findings indicate that automated analytics pipelines significantly improve forecast accuracy, end-to-end supply visibility, and optimization outcomes across multi-tier supply networks. Moreover, AI-enabled ERP systems demonstrate superior responsiveness to disruption scenarios through dynamic recalibration of planning parameters and execution rules. The paper concludes by proposing a technical integration framework that outlines key architectural layers, data flow mechanisms, and algorithmic design considerations required to develop resilient, self-adaptive supply chain systems capable of operating effectively under continuous disruption.
Ravindra Kisan Khokrale (Thu,) studied this question.