Model Trees for Identifying Exceptional Players in the NHL and NBA Drafts

  • Yejia LiuEmail author
  • Oliver Schulte
  • Chao Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11330)


Drafting players is crucial for a team’s success. We describe a data-driven interpretable approach for assessing prospects in the National Hockey League and National Basketball Association. Previous approaches have built a predictive model based on player features, or derived performance predictions from comparable players. Our work develops model tree learning, which incorporates strengths of both model-based and cohort-based approaches. A model tree partitions the feature space according to the values or learned thresholds of features. Each leaf node in the tree defines a group of players, with its own regression model. Compared to a single model, the model tree forms an ensemble that increases predictive power. Compared to cohort-based approaches, the groups of comparables are discovered from the data, without requiring a similarity metric. The model tree shows better predictive performance than the actual draft order from teams’ decisions. It can also be used to highlight the strongest points of players.


Player ranking Logistic Model Trees M5 regression trees National Hockey League National Basketball Association 


  1. 1.
    Albert, J., Glickman, M.E., Swartz, T.B., Koning, R.H.: Handbook of Statistical Methods and Analyses in Sports. CRC Press, Boca Raton (2017)CrossRefGoogle Scholar
  2. 2.
    Cervone, D., D’Amour, A., Bornn, L., Goldsberry, K.: POINTWISE: predicting points and valuing decisions in real time with NBA optical tracking data. In: MIT Sloan Sports Analytics Conference (2016)Google Scholar
  3. 3.
    Frank, E., Hall, M., Witten, I.: The WEKA workbench. Online appendix for data mining: practical machine learning tools and techniques (2016)Google Scholar
  4. 4.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 28(2), 337–407 (2000)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Green, E., Menz, M., Benz, L., Zanuttini-Frank, G., Bogaty, M.: Clustering NBA players (2016).
  6. 6.
    Green, E., Menz, M., Benz, L., Zanuttini-Frank, G., Bogaty, M.: Clustering NBA players (2017).
  7. 7.
    Greene, A.C.: The success of NBA draft picks: can college career predict NBA winners. Master’s thesis, St. Cloud State University (2015)Google Scholar
  8. 8.
    Hall, M., Frank, E., Homes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software: an update. SIGKDD Explor. 11, 10–18 (2009)CrossRefGoogle Scholar
  9. 9.
    Hollinger, J.: Calculating PER (2013).
  10. 10.
    Joyce, E., Lawrence, C.: Blending old and new: how the Florida panthers try to predict future performance at the NHL entry draft (2017)Google Scholar
  11. 11.
    Lachenbruch, P.A.: Analysis of data with excess zeros. Stat. Methods Med. Res. 11 (2002)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Liu, Y., Schulte, O., Hao, X.: Drafting NBA players based on their college performance (2018).
  13. 13.
    Loh, W.Y.: GUIDE user manual. University of Wisconsin-Madison (2017)Google Scholar
  14. 14.
    Lutz, D.: A cluster analysis of NBA players. In: MIT Sloan Sports Analytics Conference (2012)Google Scholar
  15. 15.
    Macdonald, B.: An improved adjusted plus-minus statistic for NHL players. In: MIT Sloan Sports Analytics Conference (2011)Google Scholar
  16. 16.
    Quinlan, J.R.: Learning with continuous classes, pp. 343–348. World Scientific (1992)Google Scholar
  17. 17.
    Salador, K.: Forecasting performance of international players in the NBA. In: MIT Sloan Sports Analytics Conference (2011)Google Scholar
  18. 18.
    Schuckers, M., Curro, J.: Total Hockey Rating (THoR): a comprehensive statistical rating of National Hockey League forwards and defensemen based upon all on-ice events. In: MIT Sloan Sports Analytics Conference (2013)Google Scholar
  19. 19.
    Schuckers, M.E., Statistical Sports Consulting, LLC: Draft by numbers: using data and analytics to improve National Hockey League (NHL) player selection. In: MIT Sloan Sports Analytics Conference (2016)Google Scholar
  20. 20.
    Schulte, O., Zhao, Z., SPORTLOGiQ: Apples-to-apples: clustering and ranking NHL players using location information and scoring impact. In: MIT Sloan Sports Analytics Conference (2017)Google Scholar
  21. 21.
    Shea, S., Baker, C.: Basketball Analytics: Objective and Efficient Strategies for Understanding How Teams Win. CRC Press, Boca Raton (2017)Google Scholar
  22. 22.
    Sill, J.: Improved NBA adjusted \(+/-\) using regularization and out-of-sample testing. In: MIT Sloan Sports Analytics Conference (2010)Google Scholar
  23. 23.
    Silver, N.: PECOTA 2004: A Look Back and a Look Ahead, pp. 5–10. Workman Publishers, New York (2004)Google Scholar
  24. 24.
    Thomas, A., Ventura, S., Jensen, S., Ma, S.: Competing process hazard function models for player ratings in ice hockey. Ann. Appl. Stat. 7(3), 1497–1524 (2013)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Thomas, A.C., Ventura, S.: The highway to WAR: defining and calculating the components for wins above replacement (2015).
  26. 26.
    Tingling, P., Masri, K., Martell, M.: Does order matter? An empirical analysis of NHL draft decisions. Sport Bus. Manag.: Int. J. 1(2), 155–171 (2011)CrossRefGoogle Scholar
  27. 27.
    Vinué, G., Epifanio, I.: Archetypoid analysis for sports analytics. Data Min. Knowl. Discov. 31(6), 1643–1677 (2017)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Weissbock, J.: Draft analytics: unveiling the prospect cohort success model. Technical report (2015).
  29. 29.
    Wilson, D.R.: Mining NHL draft data and a new value pick chart. Master’s thesis, University of Ottawa (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computing ScienceSimon Fraser UniversityBurnabyCanada

Personalised recommendations