Advertisement

Clustering Professional Baseball Players with SOM and Deciding Team Reinforcement Strategy with AHP

  • Kazuhiro Kohara
  • Shota Enomoto
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10933)

Abstract

In this paper, we propose an integration method that uses self-organizing maps (SOM) and the analytic hierarchy process (AHP) to cluster professional baseball players and to make decision on team reinforcement strategy. We used data of pitchers in the Japanese professional baseball teams. First, we collected data of 302 pitchers and clustered these pitchers using the following fourteen features: number of games pitched, number of wins, number of loses, number of save, number of hold, number of innings pitched, rate of strikeout, ERA (earned run average), percentage of hits a pitcher allows, WHIP (walks plus hits per inning pitched), K/BB (strikeout to walk ratio), FIP (fielding independent pitching), LOB% (left on base percentage), RSAA (runs saved above average). Second, we created pitcher maps of all teams and each team with SOM. Third, we examined main features of each cluster. Fourth, we considered team reinforcement strategies by using the pitcher maps. Finally, we used AHP to determine the team reinforcement strategy.

Keywords

Clustering Visualization Data mining Business intelligence Sport industry Baseball Decision making Self-organizing maps AHP 

References

  1. 1.
    Tolbert, B., Trafalis, T.: Predicting major league baseball championship winners through data mining. Athens J. Sports (2016). https://www.athensjournals.gr/sports/2016-3-4-1-Tolbert.pdf
  2. 2.
    Ishii, T.: Using Machine Learning Algorithms to Identify Undervalued Baseball Players (2016). http://cs229.stanford.edu/proj2016/report/Ishii-UsingMachineLearningAlgorithmsToIdentifyUndervaluedBaseballPlayers-report.pdf
  3. 3.
    Pane, M.: Trouble with the Curve: Identifying Clusters of MLB Pitchers using Improved Pitch Classification Techniques (2013). http://repository.cmu.edu/cgi/viewcontent.cgi?article=1184&context=hsshonors
  4. 4.
    Tung, D.: Data Mining Career Batting Performances in Baseball (2012). http://vixra.org/pdf/1205.0104v1.pdf
  5. 5.
    Vazquez Fernandez de Lezeta, M.: Combining Clustering and Time Series for Baseball Forecasting (2014). https://repositorio.uam.es/bitstream/handle/10486/661046/vazquez_fernandez_de_lezeta_miguel_tfg.pdf
  6. 6.
    Kohonen, T.: Self-Organizing Maps. Springer, New York (1995)CrossRefGoogle Scholar
  7. 7.
    Saaty, T.: The Analytic Hierarchy Process. McGraw-Hill, New York (1980)zbMATHGoogle Scholar
  8. 8.
    Kohara, K., Tsuda, T.: Creating product maps with self-organizing maps for purchase decision making. Trans. Mach. Learn. Data Min. 3(2), 51–66 (2010)Google Scholar
  9. 9.
    Doizoe, J., Kohara, K.: Clustering and visualization of goods with self-organizing maps. In: Proceedings of 70th Annual Convention of Information Processing Society of Japan, vol. 4, pp. 911–912 (2008). (in Japanese)Google Scholar
  10. 10.
    NPB (Nippon Professional Baseball Organization). http://npb.jp/
  11. 11.
    Professional Baseball Data. http://baseballdata.jp/
  12. 12.
    Saaty, T.: The Analytic Network Process. Expert Choice, Arlington (1996)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Chiba Institute of TechnologyNarashinoJapan

Personalised recommendations