The Role of Artificial Intelligence in Coping With Extreme Weather-Induced Cocoa Supply Chain Risks

Abstract

Poor visibility of extreme weather (EW)-induced risks and their relationships in the cocoa supply chain induces inefficient risk management and is detrimental to the resilience of the supply chain. On the basis of the resource-based view, emerging technologies can form critical organizational resources to manage these EW-induced risks effectively. Therefore, this article focuses on EW-induced supply chain risks and how artificial intelligence (AI) helps to mitigate them. First, a cognitive mapping approach is used to identify EW-induced risks, their direct links, EW occurrences, and AI capabilities that might mitigate their negative impacts. Second, the best-worst method (BWM) is adopted to rank these EW-induced risks. BWM results suggest that EW-induced risks are prominent in the midstream supply chain, followed by upstream and downstream. EW-induced transportation, farm, and demand risks are the most prevalent of the 11 risk factors, while psychological stress, market share risk, and customer dissatisfaction are the least prominent. This finding reveals that although the EW-induced risks have the greatest impact on local firms, they will be transferred to upstream and downstream firms. Furthermore, a data requirement-based evaluation of AI algorithms and a conceptual framework are developed for a systematic approach to selecting and designing an AI system for managing EW-induced supply chain risks. This study empirically discloses the multilevel relationships between AI capabilities and EW-induced supply chain risks, which can help supply chain professionals effectively manage EW-induced risks through AI.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 35 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.