Agent-Assisted Supply Chain Management: Analysis and Lessons Learned

William Groves, John Collins, Maria Gini, Wolf Ketter

Research output: Contribution to journalArticleAcademicpeer-review

38 Citations (Scopus)


This work explores 'big data' analysis in the context of supply chain management. Specifically we propose the use of agent-based competitive simulation as a tool to develop complex decision making strategies and to stress test them under a variety of market conditions. We propose an extensive set of business key performance indicators (KPIs) and apply them to analyze market dynamics. We present these results through statistics and visualizations. Our testbed is a competitive simulation, the Trading Agent Competition for Supply-Chain Management (TAC SCM), which simulates a one-year product life-cycle where six autonomous agents compete to procure component parts and sell finished products to customers. The paper provides analysis techniques and insights applicable to other supply chain environments.
Original languageEnglish
Pages (from-to)274-284
Number of pages11
JournalDecision Support Systems
Publication statusPublished - 2014


Dive into the research topics of 'Agent-Assisted Supply Chain Management: Analysis and Lessons Learned'. Together they form a unique fingerprint.

Cite this