Information Technology Reference
In-Depth Information
model, we analysed actual competition games and conducted controlled experiments
where we compete our agents with various numbers of high-price and high-volume
agents. The actual game analysis shows that our agent is able to obtain a high revenue
by offering high prices that are, nevertheless, low enough to win customer orders. In the
controlled experiments, we show that in all environments we considered, Southamp-
tonSCM is significantly better than the other two kinds of agents (with highest average
performance and lowest variance). When taken together, these evaluations show that
out pricing model is both efficient and robust.
We also believe several aspects of our agent design and strategy are applicable out-
side the confines of this competition. First of all, the general idea of the component
agent is to periodically request large orders to cover the baseline quantities needed in
low demand (steady state) markets and, at the same time, buy smaller amounts of sup-
plies when the selling price is low during the rest of the production. This mixture of
baseline and opportunistic purchasing behaviour is a common strategy in this domain
and the technology we develop for achieving this can be readily transferred. Second, we
believe our pricing model technology will also be useful in real SCM applications where
just undercutting competitors' prices can significantly improve profitability. Specifi-
cally, to apply our model in other domains, the designers of the rule base would need
to adapt the fuzzy rules to reflect the factors that are relevant to their domain. Now we
believe that customer demand and inventory level are highly likely to be critical factors
for almost all cases and thus these rules can remain unaltered. However, the time into
the game is not so broadly applicable since there is not always a rigidly fixed deadline
to real life supply chains (thus some changes may be needed here). Third, the strategy
employed by the factory agent for managing resources in uncertain and dynamically
changing environments is generally applicable. In this case, it incorporates little in the
way of domain specific knowledge and so it can remain broadly as is.
Acknowledgments
The authors would like to thank the anonymous reviewers for helpful comments and
Xudong Luo for his support during the course of the TAC/SCM competition. This re-
search is partially funded by the DIF-DTC project (8.6) on Agent-Based Control and
the ARGUS II DARP (Defence and Aerospace Research Partnership).
References
1. J. Collins, R. Arunachalam, et al. The supply chain management game for the 2005 trad-
ing agent competition. Technical Report CMU-ISRI-04-139, School of Computer Science,
Carnegie Mellon University, December 2004.
2. E. Dahlgren and P.R. Wurman.
PackaTAC: A conservative trading agent.
SIGecom Ex-
changes , 4(3):33-40, 2004.
3. M. He and N. R. Jennings. Designing a successful trading agent: A fuzzy set approach. IEEE
Transactions on Fuzzy Systems , 12(3):389-410, 2004.
4. M. He, N. R. Jennings, and H. F. Leung.
On agent-mediated electronic commerce.
IEEE
Transactions on Knowledge and Data Engineering , 15(4):985-1003, 2003.
Search WWH ::




Custom Search