Adaptive strategies for predicting bidding prices in supply chain management

ABSTRACT

Supply Chain Management (SCM) involves a number of interrelated activities from negotiating with suppliers to competing for customer orders and scheduling the manufacturing process and delivery of goods. Decision support systems for SCM need to be able to cope in uncertain, complex and highly competitive environments. Supporting dynamic strategies is a major but unresolved issue in the area. In this paper we examine two different approaches to address the issue of predicting customer offer prices that could result in orders in the domain of supply chain management. The first approach is to model the competitors' behaviour and predict their bidding prices according to the evolved models. The second one is to predict the lowest order prices for products for a number of days in the future using the time series of these prices. A set of algorithms are implemented based on Genetic Programming and Neural Networks learning techniques. The algorithms are tested in the TAC SCM simulated environment and the results are compared in terms of accuracy of prediction and execution time. Both learning techniques showed the potential for predicting prices in competitive and dynamic environments. The proposed Neural Networks algorithms demonstrate slightly better performance when tested in the TAC SCM environment compared to the algorithms implemented using Genetic Programming learning technique.

REFERENCES

• 1: Michael Benisch , James Andrews , Norman Sadeh, Pricing for customers with probabilistic valuations as a continuous knapsack problem, 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>10.1145/1151454.1151475]
• 2: Michael Benisch , Alberto Sardinha , James Andrews , Norman Sadeh, CMieux: adaptive strategies for competitive supply chain trading, ACM SIGecom Exchanges, v.6 n.1, p.1-10, June 2006 [doi>10.1145/1150735.1150737]
• 3: M. Benisch , A. Greenwald , I. Grypari , R. Lederman , V. Naroditskiy , M. Tschantz, Botticelli: A Supply Chain Management Agent, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, p.1174-1181, July 19-23, 2004, New York, New York [doi>10.1109/AAMAS.2004.77]
• 4: Collins, J., Arunachalam, R., Sadeh, N., Eriksson, J., Finne, N., and Janson, S. 2006. The Supply Chain Management Game for the 2007 Trading Agent Competition. Technical Report CMU-ISRI-07-100. Carnegie Mellon University.
• 5: Erik Dahlgren , Peter R. Wurman, PackaTAC: a conservative trading agent, ACM SIGecom Exchanges, v.4 n.3, p.38-45, February, 2004 [doi>10.1145/1120701.1120707]
• 6: Dong, R., Tai, T., Yeung W., and Parkes D. C. 2004. HarTAC -- the Harvard TAC SCM '03 Agent. In Proceedings of the Trading Agent Design and Analysis Workshop (New York, NY, USA, 20 July, 2004). TADA-03, 1--8.
• 7: 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]
• 8: Rayid Ghani, Price prediction and insurance for online auctions, Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining, August 21-24, 2005, Chicago, Illinois, USA [doi>10.1145/1081870.1081918]
• 9: Ketter, W., Collins, J., Gini, M., Gupta A., and Schrater P. 2005. Identifying and Forecasting Economic Regimes in TAC SCM. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (Edinburgh, Scotland, UK, 30 July -- 5 August, 2005), 53--60.
• 10: Philipp W. Keller , Felix-Olivier Duguay , Doina Precup, Redagent: winner of TAC SCM 2003, ACM SIGecom Exchanges, v.4 n.3, p.1-8, February, 2004 [doi>10.1145/1120701.1120703]
• 11: Wolfgang Ketter , Elena Kryzhnyaya , Steven Damer , Colin McMillen , Amrudin Agovic , John Collins , Maria Gini, MinneTAC Sales Strategies for Supply Chain TAC, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, p.1372-1373, July 19-23, 2004, New York, New York [doi>10.1109/AAMAS.2004.169]
• 12: 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]
• 13: Kontogounis, I., Chatzidimitriou, K. C., Symeonidis, A. L., and Mitkas, P. A. 2006. A Robust Agent Design for Dynamic SCM Environments. In Proceedings of the Fourth Hellenic Joint Conference on Artificial Intelligence (Heraklion, Greece, May, 2006). SETN'06, 18--20.
• 14: John R. Koza, Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge, MA, 1992
• 15: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 16: Narahari, Y., Raju, C. V. L., Ravikumar, K., and Shah, S. 2005. Dynamic pricing models for electronic business. Sadhana, 30, 2--3, 231--256. DOI= http://doi.acm.org/10.1007/BF02706246
• 17: David Pardoe , Peter Stone, Adapting in agent-based markets: a study from TAC SCM, Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems, May 14-18, 2007, Honolulu, Hawaii [doi>10.1145/1329125.1329246]
• 18: Pardoe, D. and Stone, P. 2006. Predictive Planning for Supply Chain Management. In Proceedings of the Sixteenth International Conference on Automated Planning and Scheduling (Cumbria, UK, June, 2006). ICAPS-06, 21--30.
• 19: Pardoe, D. and Stone, P. 2004. Bidding for Customer Orders in TAC SCM: A Learning Approach. In Proceedings of the Third International Joint Conference on Autonomous Agents and Multi-Agent Systems (New York, NY, July 19--23, 2004). AAMAS-04, 52--58.
• 20: Sadeh, N. M., Hildum, D. W., and Kjenstad, D. 2003. Agent-based e-supply chain decision support. Journal of Organizational Computing and Electronic Commerce, 13, 3/4, 225--42.
• 21: Massimo Santini , Andrea Tettamanzi, Genetic Programming for Financial Time Series Prediction, Proceedings of the 4th European Conference on Genetic Programming, p.361-370, April 18-20, 2001
• 22: Robert E. Schapire , Yoram Singer, BoosTexter: A Boosting-based Systemfor Text Categorization, Machine Learning, v.39 n.2-3, p.135-168, May-June 2000 [doi>10.1023/A:1007649029923]
• 23: Robert E. Schapire , Peter Stone , David A. McAllester , Michael L. Littman , János Csirik, Modeling Auction Price Uncertainty Using Boosting-based Conditional Density Estimation, Proceedings of the Nineteenth International Conference on Machine Learning, p.546-553, July 08-12, 2002
• 24: Roy Schwaerzel , Tom Bylander, Predicting currency exchange rates by genetic programming with trigonometric functions and high-order statistics, Proceedings of the 8th annual conference on Genetic and evolutionary computation, July 08-12, 2006, Seattle, Washington, USA [doi>10.1145/1143997.1144167]
• 25: Kate A. Smith , Jatinder N.D. Gupta, Neural networks in business: techniques and applications for the operations researcher, Computers and Operations Research, v.27 n.11-12, p.1023-1044, Sept.—Oct. 2000 [doi>10.1016/S0305-0548(99)00141-0]
• 26: Swaminathan, J. M., Smith, S. F., and Sadeh, N. M. 1998. Modeling Supply Chain Dynamics: A Multiagent Approach. Decision Science Journal, 29, 3, 607--632.
• 27: Michael P. Wellman , Amy Greenwald , Peter Stone, Autonomous Bidding Agents: Strategies and Lessons from the Trading Agent Competition (Intelligent Robotics and Autonomous Agents), The MIT Press, 2007
• 28: Ian H. Witten , Eibe Frank, Data mining: practical machine learning tools and techniques with Java implementations, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2000
• 29: Yao, J. T. and Tan, C. L. 2000. A Case Study on Using Neural Networks to Perform Technical Forecasting of Forex. Neurocomputing. 34, 1--4, 79--98.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.2 Types of Systems
          Subjects: Decision support (e.g., MIS)

  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.1 Models
          Subjects: Neural nets; Statistical

General Terms:
Algorithms, Design, Economics, Experimentation

Keywords:
genetic programming, neural networks, prediction, statistical time-series features, supply chain management, trading agents