Forecasting market prices in a supply chain game

ABSTRACT

Future market conditions can be a pivotal factor in making business decisions. We present and evaluate methods used by our agent, Deep Maize, to forecast market prices in the Trading Agent Competition Supply Chain Management Game. As a guiding principle we seek to exploit as many sources of available information as possible to inform predictions. Since information comes in several different forms, we integrate well-known methods in a novel way to make predictions. The core of our predictor is a nearest-neighbors machine learning algorithm that identifies historical instances with similar economic indicators. We augment this with an online learning procedure that transforms the predictions by optimizing a scoring rule. This allows us to select more relevant historical contexts using additional information available during individual games. We also explore the advantages of two different representations for predicting price distributions. One uses absolute prices, and the other uses statistics of price time series to exploit local stability. We evaluate these methods using both data from the 2005 tournament final round and additional simulations. We compare several variations of our predictor to one another and a baseline predictor similar to those used by many other tournament agents. We show substantial improvements over the baseline predictor, and demonstrate that each element of our predictor contributes to improved performance.

REFERENCES

• 1: I. Alon, M. Qi, and R. J. Sandowski. Forecasting aggregate retail sales: A comparison of artificial neural networks and traditional methods. Retailing and Consumer Services, 8:147--156, 2001.
• 2: J. M. Bates and C. W. J. Granger. The combination of forecasts. Operations Research, 20(4):451--468, 1969.
• 3: Michael Benisch , Amy Greenwald , Victor Naroditskiy , Michael Carl Tschantz, A stochastic programming approach to scheduling in TAC SCM, Proceedings of the 5th ACM conference on Electronic commerce, May 17-20, 2004, New York, NY, USA [doi>10.1145/988772.988796]
• 4: Michael Benisch , Alberto Sardinha , James Andrews , Norman Sadeh, CMieux: adaptive strategies for competitive supply chain trading, Proceedings of the 8th international conference on Electronic commerce: The new e-commerce: innovations for conquering current barriers, obstacles and limitations to conducting successful business on the internet, August 13-16, 2006, Fredericton, New Brunswick, Canada [doi>10.1145/1151454.1151476]
• 5: P. J. Brockwell and R. A. Davis. Introduction to Time Series and Forecasting. Springer-Verlag, 1996.
• 6: D. A. Burke, K. N. Brown, B. Hnich, and A. Tarim. Learning market prices for a real-time supply chain management trading agent. In AAMAS-06 Workshop on Trading Agent Design and Analysis, 2006.
• 7: C. Chatfield. Time-Series Forecasting. Chapman & Hall/CRC, 2001.
• 8: Shih-Fen Cheng , Evan Leung , Kevin M. Lochner , Kevin O'Malley , Daniel M. Reeves , Julian L. Schvartzman , Michael P. Wellman, Walverine: a Walrasian trading agent, Decision Support Systems, v.39 n.2, p.169-184, April 2005 [doi>10.1016/j.dss.2003.10.005]
• 9: R. T. Clemen and R. L. Winkler. Combining probability distributions from experts in risk analysis. Risk Analysis, 19(2):187--203, 1999.
• 10: J. Collins, R. Arunachalam, N. Sadeh, J. Eriksson, N. Finne, and S. Janson. The supply chain management game for the 2005 trading agent competition. Technical Report CMU-ISRI-04-139, Carnegie Mellon University, 2004.
• 11: Joakim Eriksson , Niclas Finne , Sverker Janson, Evolution of a supply chain management game for the trading agent competition, AI Communications, v.19 n.1, p.1-12, January 2006
• 12: Robin Hanson, Combinatorial Information Market Design, Information Systems Frontiers, v.5 n.1, p.107-119, January 2003 [doi>10.1023/A:1022058209073]
• 13: T. Hastie, R. Tibshirani, and J. Friedman. Elements of Statistical Learning. Springer-Verlag, 2001.
• 14: Minghua He , Alex Rogers , Xudong Luo , Nicholas R. Jennings, Designing a successful trading agent for supply chain management, Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, May 08-12, 2006, Hakodate, Japan [doi>10.1145/1160633.1160843]
• 15: W. Ketter, J. Collins, M. Gini, A. Gupta, and P. Schrater. Identifying and forecasting economic regimes in TAC SCM. In IJCAI-05 workshop on Trading Agent Design and Analysis, 2005.
• 16: Christopher Kiekintveld , Jason Miller , Patrick R. Jordan , Michael P. Wellman, Controlling a supply chain agent using value-based decomposition, Proceedings of the 7th ACM conference on Electronic commerce, p.208-217, June 11-15, 2006, Ann Arbor, Michigan, USA [doi>10.1145/1134707.1134730]
• 17: C. Kiekintveld, Y. Vorobeychik, and M. P. Wellman. An analysis of the 2004 supply chain management trading agent competition. In IJCAI 2005 Workshop on Trading Agent Design and Analysis, 2005.
• 18: C. Kiekintveld, M. P. Wellman, S. Singh, J. Estelle, Y. Vorobeychik, V. Soni, and M. Rudary. Distributed feedback control for decision making on supply chains. In Fourteenth International Conference on Automated Planning and Scheduling, pages 384--392, 2004.
• 19: F. J. Nogales, J. Contreras, A. J. Conejo, and R. Espinola. Forecasting next-day electricity prices by time series models. IEEE Transactions on Power Systems, 17(2):342--348, 2002.
• 20: D. Pardoe and P. Stone. Bidding for customer orders in TAC SCM. In Agent Mediated Electronic Commerce VI: Theories for and Engineering of Distributed Mechanisms and Systems (AMEC 2004), 2005.
• 21: D. Pardoe and P. Stone. An autonomous agent for supply chain mangement. Technical report, University of Texas, 2006.
• 22: D. Pardoe and P. Stone. Predictive planning for supply chain management. In Proceedings of the International Conference on Automated Planning and Scheduling, June 2006.
• 23: P. Stone, R. E. Schapire, M. L. Littman, J. A. Csirik, and D. McAllester. Decision-theoretic bidding based on learned density models in simultaneous, interacting auctions. Journal of Artificial Intelligence Research, 19:209--242, 2003.
• 24: Patrick R. Jordan , Christopher Kiekintveld , Michael P. Wellman, Empirical game-theoretic analysis of the TAC Supply Chain game, Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems, May 14-18, 2007, Honolulu, Hawaii [doi>10.1145/1329125.1329359]
• 25: M. P. Wellman, D. M. Reeves, K. M. Lochner, and Y. Vorobeychik. Price prediction in a trading agent competition. Journal of Artificial Intelligence Research, 21:19--36, 2004.

INDEX TERMS

General Terms:
Economics, Experimentation, Measurement

Keywords:
forecasting, machine learning, markets, price prediction, supply chain management, trading agent competition