Applied Intelligence

, Volume 38, Issue 3, pp 465–477 | Cite as

Using a case-based reasoning approach for trading in sports betting markets

  • Juan M. Alberola
  • Ana Garcia-Fornes


The sports betting market has emerged as one of the most lucrative markets in recent years. Trading in sports betting markets entails predicting odd movements in order to bet on an outcome, whilst also betting on the opposite outcome, at different odds in order to make a profit, regardless of the final result. These markets are mainly composed by humans, which take decisions according to their past experience in these markets. However, human rational reasoning is limited when taking quick decisions, being influenced by emotional factors and offering limited calibration capabilities for estimating probabilities. In this paper, we show how artificial techniques could be applied to this field and demonstrate that they can outperform even the bevahior of high-experienced humans. To achieve this goal, we propose a case-based reasoning model for trading in sports betting markets, which is integrated in an agent to provide it with the capabilities to take trading decisions based on future odd predictions. In order to test the performance of the system, we compare trading decisions taken by the agent with trading decisions taken by human traders when they compete in real sports betting markets.


Sports betting markets Trading Odds prediction Case-based reasoning Humans 



This work has been partially supported by CONSOLIDER-INGENIO 2010 under grant CSD2007-00022, and project TIN2011-27652-C03-01. Juan M. Alberola has received a grant from Ministerio de Ciencia e Innovación de España (AP2007-00289).


  1. 1.
    Aamodt A (1990) Knowledge-intensive case-based reasoning and sustained learning. In: Topics in case-based reasoning. Springer, Berlin, pp 274–288 Google Scholar
  2. 2.
    Aamodt A, Plaza E (1994) Case-based reasoning; foundational issues, methodological variations, and system approaches. AI Commun 7(1):39–59 Google Scholar
  3. 3.
    Ahn JJ, Byun HW, Oh KJ, Kim TY (2012) Bayesian forecaster using class-based optimization. Appl Intell 36(3):553–563 CrossRefGoogle Scholar
  4. 4.
    Alberola JM, Garcia-Fornes A, Espinosa A (2010) Price prediction in sports betting markets. In: Proceedings of the 8th German conference on multiagent system technologies, pp 197–208 CrossRefGoogle Scholar
  5. 5.
    Arias-Aranda D, Castro JL, Navarro M, Zurita JM (2009) A cbr system for knowing the relationship between flexibility and operations strategy. In: Proceedings of the 18th international symposium on foundations of intelligent systems, ISMIS’09, pp 463–472 CrossRefGoogle Scholar
  6. 6.
    Ates C (2004) Prediction markets are only human: subadditivity in probability judgments. In: MSC in finance and international business Google Scholar
  7. 7.
    Berlemann M, Schmidt C (2001) Predictive accuracy of political stock markets—empirical evidence from a European perspective. Technical report 2001-57 Google Scholar
  8. 8.
  9. 9.
    Chen Y, Goel S, Pennock D (2008) Pricing combinatorial markets for tournaments. In: STOC’08: proceedings of the 40th annual ACM symposium on theory of computing. ACM Press, New York, pp 305–314 Google Scholar
  10. 10.
    Debnath S, Pennock DM, Giles CL, Lawrence S (2003) Information incorporation in online in-game sports betting markets. In: Proceedings of the 4th ACM conference on electronic commerce, EC ’03. ACM Press, New York, pp 258–259. doi: 10.1145/779928.779987 CrossRefGoogle Scholar
  11. 11.
    Fischoff B, Slovic P, Lichtenstein S (1977) Knowing with certainty: the appropriateness of extreme confidence. J Exp Psychol Human Percept Perform 3:552–564 CrossRefGoogle Scholar
  12. 12.
    Forsythe R, Rietz T, Ross T (1999) Wishes, expectations and actions: a survey on price formation in election stock markets. J Econ Behav Organ 39(1):83–110 CrossRefGoogle Scholar
  13. 13.
    Fortnow L, Kilian J, Pennock DM, Wellman MP (2005) Betting Boolean-style: a framework for trading in securities based on logical formulas. Decis Support Syst 39(1):87–104. doi: 10.1016/j.dss.2004.08.010 CrossRefGoogle Scholar
  14. 14.
    Gayer G (2010) Perception of probabilities in situations of risk: a case based approach. Games Econ Behav 68(1):130–143 MathSciNetzbMATHCrossRefGoogle Scholar
  15. 15.
    Guo M, Pennock D (2009) Combinatorial prediction markets for event hierarchies. In: Proc of the 8th AAMAS’09. Int foundation for autonomous agents and multiagent systems, pp 201–208 Google Scholar
  16. 16.
    Huang W, Lai K, Nakamori Y, Wang S (2004) Forecasting foreign exchange rates with artificial neural networks: a review. Int J Inf Technol Decis Mak 3(1):145–165 CrossRefGoogle Scholar
  17. 17.
    Hüllermeier E (2007) Case-based approximate reasoning. Theory and decision library, vol 44. Springer, Berlin Google Scholar
  18. 18.
    Kim K-J, Ahn H (2012) Simultaneous optimization of artificial neural networks for financial forecasting. Appl Intell 36(4):887–898 MathSciNetCrossRefGoogle Scholar
  19. 19.
    LeBaron B (1998) Agent based computational finance: suggested readings and early research. J Econ Dyn Control Google Scholar
  20. 20.
    Liu Y, Yang C, Yang Y, Lin F, Du X, Ito T (2012) Case learning for cbr-based collision avoidance systems. Appl Intell 36(2):308–319 CrossRefGoogle Scholar
  21. 21.
    Love BC (2008) Behavioural finance and sports betting markets. In: MSC in finance and international business Google Scholar
  22. 22.
    Luque C, Valls JM, Isasi P (2011) Time series prediction evolving Voronoi regions. Appl Intell 34(1):116–126 CrossRefGoogle Scholar
  23. 23.
    Mantaras RLD, McSherry D, Bridge D, Leake D, Smyth B, Craw S, Faltings B, Maher M, Lou C, Forbus MCK, Keane M, Aamodt A, Watson I (2005) Retrieval, reuse, revision and retention in case-based reasoning. Knowl Eng Rev 20(3):215–240 CrossRefGoogle Scholar
  24. 24.
    Moody J (1995) Economic forecasting: challenges and neural network solutions. In: Proceedings of the international symposium on artificial neural networks Google Scholar
  25. 25.
    Ontañón S, Plaza E (2009) Argumentation-based information exchange in prediction markets. Argument Multi-Agent Syst 5384:181–196 CrossRefGoogle Scholar
  26. 26.
    Ontañón S, Plaza E (2011) An argumentation framework for learning, information exchange, and joint-deliberation in multi-agent systems. Multiagent Grid Syst 7:95–108 zbMATHGoogle Scholar
  27. 27.
    Palmer R, Arthur W, Holland J, Lebaron B, Tayler P (1994) Artificial economic life: a simple model of a stock market. Physica D 75:264–274 zbMATHCrossRefGoogle Scholar
  28. 28.
    Pennock D, Debnath S, Glover E, Giles C (2002) Modelling information incorporation in markets, with application to detecting and explaining events. In: Proceedings of the 18th annual conference on uncertainty in artificial intelligence (UAI-02), San Francisco, CA. Morgan Kaufmann, San Mateo, pp 404–405 Google Scholar
  29. 29.
    Pennock DM, Lawrence S, Nielsen FÅ, Giles CL (2001) Extracting collective probabilistic forecasts from web games. In: Proceedings of the seventh ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’01. ACM Press, New York, pp 174–183. doi: 10.1145/502512.502537 CrossRefGoogle Scholar
  30. 30.
    Plott CR (2000) Markets as information gathering tools. South Econ J 67(1):2–15 Google Scholar
  31. 31.
    Qian B, Rasheed K (2007) Stock market prediction with multiple classifiers. Appl Intell 26(1):25–33 CrossRefGoogle Scholar
  32. 32.
    Raudys S, Zliobaite I (2006) The multi-agent system for prediction of financial time series. In: ICAISC, vol 4029. Springer, Berlin, pp 653–662 Google Scholar
  33. 33.
    Schmidt C, Werwatz A (2002) How accurate do markets predict the outcome of an event? The euro 2000 soccer championship experiment, 2002-09. Max Planck Institute of Economics, Strategic Interaction Group.
  34. 34.
    Shiu SCK, Pal SK (2004) Case-based reasoning: concepts, features and soft computing. Appl Intell 21(3):233–238 CrossRefGoogle Scholar
  35. 35.
    Wellman MP, Reeves DM, Lochner KM, Vorobeychik Y (2004) Price prediction in a trading agent competition. J Artif Intell Res 21:19–36 Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Departament de Sistemes Informàtics i ComputacióUniversitat Politècnica de ValènciaValènciaSpain

Personalised recommendations