A strategy in sports betting with the nearest neighbours search and genetic algorithms

• Autorzy: Borycki D.
• Języki publikacji: EN

Abstrakty

EN

The point of sports betting is not merely to correctly predict the outcome of a game, but to actually win on a bet. We propose a model of sports betting that uses the nearest neighbours search and genetic algorithms to do the job. It uses data on the teams playing, their respective formations, individual players, results of previous games, as well as odds offered by bookmakers. The model has been trained using the data from the seasons 2002/03 until 2008/09 of the English Premier League and tested against the already played games of the seasons 2009/10 and 2010/11.

Słowa kluczowe

EN

sports betting; nearest neighbour search; genetic algorithm; English Premier League

• Wydawca: Wydawnictwo UMCS
• Czasopismo: Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica
• Rocznik: 2011
• Tom: Vol. 11, no. 1
• Strony: 7--13
• Opis fizyczny: Bibliogr. 5 poz., rys., tab.

Twórcy

autor

Borycki D.

• Jagiellonian University, Faculty of Physics, Astronomy and Applied Computer Science, Reymonta 4, 30-059 Kraków, Poland

Bibliografia

• [1] Min B., Kim J., Choe C., Eom H., McKay R. I., A Compound Framework for Sports Prediction: The Case Study of Football, Knowledge-Based Systems, 21(7) (2008): 551.
• [2] Rotshtein A. P., Posner M., Rakityanskaya A. B., Football Predictions Based on a Fuzzy Model with Genetic and Neural Tuning, Cybernetics and Systems Analysis 41(4) (2005): 619.
• [3] Rue H., Salvesen O., Prediction and retrospective analysis of soccer matches in a league, The Statistician 49(3) (2000): 399.
• [4] Larose D. T., Discovering Knowledge in Data. An Introduction to DATA MINING, Chapter 5.
• [5] Larose D. T., Data mining methods and models, Chapter 6.