Improving Supply Chain Resilience through Artificial Intelligence and Big Data: A Total Interpretive Structural Model

Document Type : Original Article

Authors

1 Department of Management, Faculty of Administrative Sciences and Economics, Arak University, Arak, Iran

2 Management department. Faculty of Administrative Sciences and Economics, Arak University, Arak. Iran

Abstract

Background and Objectives: Today, there is a growing concern in the supply chain due to disruptions, which requires appropriate tools to support the supply chain to increase its resilience. This study examines the role of artificial intelligence and big data analytics in creating resilient supply chains in Iranian SMEs.
Materials and Methods: The present study is applied and developmental in terms of purpose and in terms of the nature of the data, it is qualitative. The statistical population of the study is managers of small and medium-sized companies in Iran, Sampling carried out using purposive method and a total of 15 people interviewed to achieve the theoretical adequacy criterion. The Total Interpretive Structural Modeling method was used to conduct this research.
Results: Factors identified in 12 dimensions and then, using the total interpretive structural modeling method, 7 levels of classification and their relationship determined. The Supply Chain Analytics (SCA) factor placed at level 7, Demand Forecasting (DF), Consumer Behavior (CB), and Operations and Planning (OP) placed at level 6, Visibility (VIS) placed at level 5, Periodic Monitoring (PM) placed at level 4, Point-Of-Sale data analytics (POS) and Inventory Management (INV) located at Level 3, Efficiency (ECY), Transportation (TRN), and Route Optimization (RO) located at Level 2 and Supply Chain Resilience (SCR) located at Level 1.
Conclusion: Practical suggestions for improving supply chain resilience include: Using machine learning models to analyze sales data, customer behavior, and market conditions; Combining internal and external data for more accurate and timely forecasts; Designing different scenarios based on data analysis and preparing alternative plans; Using route and scheduling optimization algorithms based on traffic and environmental data; Big data analysis to select suppliers and routes with the lowest risk and cost; Employing robots and intelligent systems to perform warehousing, ordering, and inventory control operations; training supply chain personnel in data analysis and artificial intelligence applications.

Keywords

Strategic Value Chain Management
Volume 2, Issue 3 - Serial Number 6
October 2025
Pages 93-117

Files

History

  • Receive Date: 21 September 2025
  • Revise Date: 09 October 2025
  • Accept Date: 14 October 2025
  • Publish Date: 23 October 2025

Share

How to cite

Statistics