Downloads: 1 | Views: 71 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Analysis Study Research Paper | Information Technology | United States of America | Volume 12 Issue 1, January 2023 | Rating: 5 / 10
Explainable AI for Time Series Analysis in Real - Time Supply Chain Optimization
Abstract: The integration of Explainable AI (XAI) into time series analysis presents transformative opportunities for real - time supply chain optimization. This research paper explores how XAI methodologies can be applied to time series data to enhance decision - making processes in supply chain management. We delve into the challenges faced by current supply chain systems, the role of time series analysis, and the critical need for interpretability in AI models. By examining state - of - the - art XAI techniques and their practical applications in supply chain scenarios, this paper demonstrates how transparency in AI can lead to more efficient and robust supply chain operations. The paper also provides empirical evidence and case studies to illustrate the practical benefits of XAI in real - world supply chain environments. Through detailed analyses, we show how XAI techniques such as SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model - agnostic Explanations), and counterfactual explanations improve the understanding of complex AI models. This enhanced understanding not only fosters greater trust in AI - driven decisions but also empowers supply chain managers to identify potential areas for optimization, mitigate risks, and adapt to changing market conditions with agility. The insights gained from XAI contribute to creating more resilient and responsive supply chains, capable of maintaining efficiency and reliability even in the face of uncertainties.
Keywords: Explainable AI, time series analysis, supply chain optimization, AI interpretability, SHAP and LIME
Edition: Volume 12 Issue 1, January 2023,
Pages: 1320 - 1325