Abstract
There seems to be an upper limit to predicting the outcome of matches in (semi-)professional sports. A number of works have proposed that this is due to chance and attempts have been made to simulate the distribution of win percentages to identify the most likely proportion of matches decided by chance. We argue that the approach that has been chosen so far makes some simplifying assumptions that cause its result to be of limited practical value, especially for settings where teams do not play all possible opponents. Instead, we propose to use clustering of statistical team profiles and observed scheduling information to derive limits on the predictive accuracy for particular seasons, which can be used to assess the performance of predictive models on those seasons. Using NCAA basketball data, we show that the resulting simulated distributions are much closer to the observed distributions and give higher assessments of chance and tighter limits on predictive accuracy. We also show similar results for the NBA.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For details for Weissbock’s work, we direct the reader to [12].
- 2.
The choice of seasons is due to presentation concerns, especially in the case of visualizations. Other/additional seasons exhibit similar phenomena.
- 3.
Other seasons show similar behavior, so we treat 2008 as a representative example.
- 4.
The results for other seasons can be found in Appendix A.
- 5.
Although some might be similar enough to be merged.
References
Aoki, R.Y., Assuncao, R.M., Vaz de Melo, P.O.: Luck is hard to beat: the difficulty of sports prediction. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1367–1376 (2017)
Burke, B.: Luck and NFL outcomes 1. http://www.advancedfootballanalytics.com/2007/08/luck-and-nfl-outcomes.html. Accessed 15 May 2023
Burke, B.: Luck and NFL outcomes 1. http://www.advancedfootballanalytics.com/2007/08/luck-and-nfl-outcomes-2.html. Accessed 15 May 2023
Burke, B.: Luck and NFL outcomes 1. http://www.advancedfootballanalytics.com/2007/08/luck-and-nfl-outcomes-3.html. Accessed 15 May 2023
Csurilla, G., Boros, Z., Fűrész, D.I., Gyimesi, A., Raab, M., Sterbenz, T.: How much is winning a matter of luck? a comparison of 3\(\times \) 3 and 5v5 basketball. Int. J. Environ. Res. Public Health 20(4), 2911 (2023)
Frank, E., Witten, I.H.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, Burlington (1999)
Gilbert, D.E., Wells, M.T.: Ludometrics: luck, and how to measure it. J. Quant. Anal. Sports 15(3), 225–237 (2019)
Mauboussin, M.J.: The Success Equation: Untangling Skill and Luck in Business, Sports, and Investing. Harvard Business Review Press, Brighton (2012)
Oh, M.H., Keshri, S., Iyengar, G.: Graphical model for basketball match simulation. In: MIT Sloan Sports Analytics Conference (2015)
Pomeroy, K.: Advanced analysis of college basketball. http://kenpom.com
Sarkar, S., Kamath, S.: Does luck play a role in the determination of the rank positions in football leagues? A study of Europe’s ‘big five’. Ann. Oper. Res. 325, 1–16 (2021)
Weissbock, J.: Theoretical predictions in machine learning for the NHL: Part ii. http://nhlnumbers.com/2013/8/6/theoretical-predictions-in-machine-learning-for-the-nhl-part-ii. Accessed 22 June 2015
Weissbock, J., Inkpen, D.: Combining textual pre-game reports and statistical data for predicting success in the national hockey league. In: Sokolova, M., van Beek, P. (eds.) AI 2014. LNCS (LNAI), vol. 8436, pp. 251–262. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06483-3_22
Zimmermann, A.: Basketball predictions in the NCAAB and NBA: similarities and differences. Stat. Anal. Data Min. 9(5), 350–364 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Clustered schedules for different seasons, unconstrained EM
A Clustered schedules for different seasons, unconstrained EM
See Tables 7, 8, 9, 10 and 11.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zimmermann, A. (2023). Chance and the Predictive Limit in Basketball (Both College and Professional). In: Bifet, A., Lorena, A.C., Ribeiro, R.P., Gama, J., Abreu, P.H. (eds) Discovery Science. DS 2023. Lecture Notes in Computer Science(), vol 14276. Springer, Cham. https://doi.org/10.1007/978-3-031-45275-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-45275-8_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45274-1
Online ISBN: 978-3-031-45275-8
eBook Packages: Computer ScienceComputer Science (R0)