Forecasting market prices in a supply chain game

Predicting the uncertain and dynamic future of market conditions on the supply chain, as reflected in prices, is an essential component of effective operational decision-making. We present and evaluate methods used by our agent, Deep Maize, to forecast market prices in the trading agent competition supply chain management game (TAC/SCM). We employ a variety of machine learning and representational techniques to exploit as many types of information as possible, integrating well-known methods in novel ways. We evaluate these techniques through controlled experiments as well as performance in both the main TAC/SCM tournament and supplementary Prediction Challenge. Our prediction methods demonstrate strong performance in controlled experiments and achieved the best overall score in the Prediction Challenge.

[1]  Maria L. Gini,et al.  A predictive empirical model for pricing and resource allocation decisions , 2007, ICEC.

[2]  David P. Stone.  An Autonomous Agent for Supply Chain Management , 2007 .

[3]  Michael P. Wellman,et al.  Empirical game-theoretic analysis of the TAC Supply Chain game , 2007, AAMAS '07.

[4]  M. Qi,et al.  Forecasting aggregate retail sales , 2001 .

[5]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[6]  Michael P. Wellman,et al.  Distributed Feedback Control for Decision Making on Supply Chains , 2004, ICAPS.

[7]  Peter Stone,et al.  Adapting Price Predictions in TAC SCM , 2007, AMEC/TADA.

[8]  Peter Stone,et al.  The 2007 TAC SCM Prediction Challenge , 2008, AMEC/TADA.

[9]  Robert L. Winkler,et al.  Combining Probability Distributions From Experts in Risk Analysis , 1999 .

[10]  M. P. Wellman,et al.  Price Prediction in a Trading Agent Competition , 2004, J. Artif. Intell. Res..

[11]  Michael P. Wellman,et al.  Empirical Game-Theoretic Analysis of the TAC Market Games , 2006 .

[12]  Michael P. Wellman,et al.  Walverine: a Walrasian trading agent , 2003, AAMAS '03.

[13]  Michael Carl Tschantz,et al.  A stochastic programming approach to scheduling in TAC SCM , 2004, EC '04.

[14]  Nicholas R. Jennings,et al.  Designing a successful trading agent for supply chain management , 2006, AAMAS '06.

[15]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[16]  Jason Miller,et al.  Forecasting market prices in a supply chain game , 2007, AAMAS '07.

[17]  Michael P. Wellman,et al.  Autonomous bidding agents - strategies and lessons from the trading agent competition , 2007 .

[18]  Doina Precup,et al.  RedAgent-2003: an autonomous, market-based supply-chain management agent , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[19]  Maria L. Gini,et al.  Identifying and Forecasting Economic Regimes in TAC SCM , 2005, AMEC@AAMAS/TADA@IJCAI.

[20]  Chris Chatfield,et al.  Time‐series forecasting , 2000 .

[21]  Peter Stone,et al.  Bidding for customer orders in TAC SCM , 2004, AAMAS'04.

[22]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[23]  Joakim Eriksson,et al.  Evolution of a supply chain management game for the Trading Agent Competition , 2006, AI Commun..

[24]  Marko Robnik-Sikonja,et al.  An adaptation of Relief for attribute estimation in regression , 1997, ICML.

[25]  Michael P. Wellman,et al.  An analysis of the 2004 supply chain management trading agent competition , 2005, NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society.

[26]  Robin Hanson,et al.  Combinatorial Information Market Design , 2003, Inf. Syst. Frontiers.

[27]  Edmund H. Durfee,et al.  Model Selection in an Information Economy: Choosing What to Learn , 2002, Comput. Intell..

[28]  J. Contreras,et al.  Forecasting Next-Day Electricity Prices by Time Series Models , 2002, IEEE Power Engineering Review.

[29]  Norman M. Sadeh,et al.  CMieux: Adaptive strategies for competitive supply chain trading , 2009, Electron. Commer. Res. Appl..

[30]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[31]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[32]  Maria Gini,et al.  Identification and prediction of economic regimes to guide decision making in multi-agent marketplaces , 2007 .

[33]  Jason Miller,et al.  Controlling a supply chain agent using value-based decomposition , 2006, EC '06.

[34]  Peter Stone,et al.  TacTex-05: A Champion Supply Chain Management Agent , 2006, AAAI.

[35]  Rayid Ghani,et al.  Price prediction and insurance for online auctions , 2005, KDD '05.

[36]  Michael P. Wellman,et al.  Self-Confirming Price Prediction for Bidding in Simultaneous Ascending Auctions , 2005, UAI.

[37]  D. Rubinfeld,et al.  Econometric models and economic forecasts , 2002 .

[38]  Kenneth N. Brown,et al.  Learning Market Prices for a Real-time Supply Chain Management Trading Agent ? , 2006 .

[39]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[40]  David A. McAllester,et al.  Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions , 2003, J. Artif. Intell. Res..

[41]  Perry J. Kaufman,et al.  Trading Systems and Methods , 1997 .

[42]  John Collins,et al.  The Supply Chain Management Game for the 2007 Trading Agent Competition , 2004 .