Identifying and Forecasting Economic Regimes in TAC SCM

  • Wolfgang Ketter
  • John Collins
  • Maria Gini
  • Alok Gupta
  • Paul Schrater
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3937)


We present methods for an autonomous agent to identify dominant market conditions, such as over-supply or scarcity, and to forecast market changes. We show that market conditions can be characterized by distinguishable statistical patterns that can be learned from historic data and used, together with real-time observable information, to identify the current market regime and to forecast market changes. We use a Gaussian Mixture Model to represent the probabilities of market prices and, by clustering these probabilities, we identify different economic regimes. We show that the regimes so identified have properties that correlate with market factors that are not directly observable. We then present methods to predict regime changes. We validate our methods by presenting experimental results obtained with data from the Trading Agent Competition for Supply Chain Management.


Gaussian Mixture Model Autonomous Agent Market Segment Current Regime Regime Switch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sadeh, N., Arunachalam, R., Eriksson, J., Finne, N., Janson, S.: TAC-03: A supply-chain trading competition. AI Magazine 24(1), 92–94 (2003)Google Scholar
  2. 2.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B 39(1), 1–38 (1977)MathSciNetMATHGoogle Scholar
  3. 3.
    Levinson, S.E.: Continuously variable duration hidden markov models for automatic speech recognition. Comput. Speech Lang. 1(1), 29–45 (1986)CrossRefGoogle Scholar
  4. 4.
    Pauwels, K., Hanssens, D.: Windows of Change inMatureMarkets. In: European Marketing Academy Conf., Braga, Portugal (2002)Google Scholar
  5. 5.
    Cherkassky, V., Mulier, F.: Learning from data – Concepts, Theory, and Methods. John Wiley & Sons, INC., New York (1998)MATHGoogle Scholar
  6. 6.
    Ng, A., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. of the 17th Int’l. Conf. on Machine Learning, Palo Alto, pp. 663–670 (2000)Google Scholar
  7. 7.
    Carmel, D., Markovitch, S.: Learning models of opponent’s strategy in game playing. Technical report, Technion-Israel Institute of Technology (1993)Google Scholar
  8. 8.
    Chajewska, U., Koller, D., Ormoneit, D.: Learning an agent’s utility function by observing behavior. In: Proc. of the 18th Int’l. Conf. on Machine Learning, Lafayette, pp. 35–42 (2001)Google Scholar
  9. 9.
    von Neumann, J., Morgenstern, O.: Theory of Games and Economic Behavior, 2nd edn. Princeton University Press, Princeton (1947)MATHGoogle Scholar
  10. 10.
    Pardoe, D., Stone, P.: Bidding for Customer Orders in TAC SCM: A Learning Approach. In: Workshop on Trading Agent Design and Analysis at AAMAS, New York, pp. 52–58 (2004)Google Scholar
  11. 11.
    Benisch, M., Greenwald, A., Grypari, I., Lederman, R., Naroditskiy, V., Tschantz, M.: Botticelli: A supply chain management agent designed to optimize under uncertainty. ACM Trans. on Computational Logic 4(3), 29–37 (2004)Google Scholar
  12. 12.
    Ketter, W., Kryzhnyaya, E., Damer, S., McMillen, C., Agovic, A., Collins, J., Gini, M.: MinneTAC sales strategies for supply chain TAC. In: Proc. of the Third Int’l. Conf. on Autonomous Agents and Multi-Agent Systems, New York, pp. 1372–1373 (2004)Google Scholar
  13. 13.
    Ketter, W., Kryzhnyaya, E., Damer, S., McMillen, C., Agovic, A., Collins, J., Gini, M.: Analysis and design of supply-driven strategies in TAC-SCM. In: Workshop: Trading Agent Design and Analysis at the Third Int’l. Conf. on Autonomous Agents and Multi-Agent Systems, New York, pp. 44–51 (2004)Google Scholar
  14. 14.
    Dahlgren, E., Wurman, P.: PackaTAC: A conservative trading agent. SIGecom Exchanges 4(3), 33–40 (2004)CrossRefGoogle Scholar
  15. 15.
    Wellman, M.P., Estelle, J., Singh, S., Vorobeychik, Y., Kiekintveld, C., Soni, V.: Strategic interactions in a supply chain game. Computational Intelligence 21(1), 1–26 (2005)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wolfgang Ketter
    • 1
  • John Collins
    • 1
  • Maria Gini
    • 1
  • Alok Gupta
    • 2
  • Paul Schrater
    • 1
  1. 1.Department of Computer Science and EngineeringUSA
  2. 2.Department of Information and Decision SciencesUniversity of MinnesotaMinneapolisUSA

Personalised recommendations