LinNet: Probabilistic Lineup Evaluation Through Network Embedding

  • Konstantinos PelechrinisEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11053)


Which of your team’s possible lineups has the best chances against each of your opponent’s possible lineups? To answer this question, we develop LinNet (which stands for LINeup NETwork). LinNet exploits the dynamics of a directed network that captures the performance of lineups during their matchups. The nodes of this network represent the different lineups, while an edge from node B to node A exists if lineup \({\lambda }_A\) has outperformed lineup \({\lambda }_B\). We further annotate each edge with the corresponding performance margin (point margin per minute). We then utilize this structure to learn a set of latent features for each node (i.e., lineup) using the node2vec framework. Consequently, using the latent, learned features, LinNet builds a logistic regression model for the probability of lineup \({\lambda }_A\) outperforming lineup \({\lambda }_B\). We evaluate the proposed method by using NBA lineup data from the five seasons between 2007–08 and 2011–12. Our results indicate that our method has an out-of-sample accuracy of 68%. In comparison, utilizing simple network centrality metrics (i.e., PageRank) achieves an accuracy of just 53%, while using the adjusted plus-minus of the players in the lineup for the same prediction problem provides an accuracy of only 55%. We have also explored the adjusted lineups’ plus-minus as our predictors and obtained an accuracy of 59%. Furthermore, the probability output of LinNet is well-calibrated as indicated by the Brier score and the reliability curve. One of the main benefits of LinNet is its generic nature that allows it to be applied in different sports since the only input required is the lineups’ matchup network, i.e., not any sport-specific features are needed.


Network science Network embedding Sports analytics Probabilistic models 


  1. 1.
    NBA advanced stats: Lineup efficiency. Accessed 04 Apr 2018
  2. 2.
    Agresti, A.: An Introduction to Categorical Data Analysis. Wiley Series in Probability and Statistics. Wiley-Interscience, Hoboken (2007)CrossRefGoogle Scholar
  3. 3.
    Brier, G.W.: Verification of forecasts expressed in terms of probability. Mon. Weather Rev. 78(1), 1–3 (1950)CrossRefGoogle Scholar
  4. 4.
    Fewell, J.H., Armbruster, D., Ingraham, J., Petersen, A., Waters, J.S.: Basketball teams as strategic networks. PloS One 7(11), e47445 (2012)CrossRefGoogle Scholar
  5. 5.
    Gonçalves, B., Coutinho, D., Santos, S., Lago-Penas, C., Jiménez, S., Sampaio, J.: Exploring team passing networks and player movement dynamics in youth association football. PloS One 12(1), e0171156 (2017)CrossRefGoogle Scholar
  6. 6.
    Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864. ACM (2016)Google Scholar
  7. 7.
    Le, H.M., Yue, Y., Carr, P., Lucey, P.: Coordinated multi-agent imitation learning. In: International Conference on Machine Learning, pp. 1995–2003 (2017)Google Scholar
  8. 8.
  9. 9.
    Mason, S.J.: On using “climatology" as a reference strategy in the Brier and ranked probability skill scores. Mon. Weather Rev. 132(7), 1891–1895 (2004)CrossRefGoogle Scholar
  10. 10.
    Mehrasa, N., Zhong, Y., Tung, F., Bornn, L., Mori, G.: Deep learning of player trajectory representations for team activity analysis (2018)Google Scholar
  11. 11.
    Oliver, D.: Basketball on Paper: Rules and Tools for Performance Analysis. Potomac Books, Lincoln (2004)Google Scholar
  12. 12.
    Pelechrinis, K.: Lineup evaluations through in-game win probability models and bayesian adjustment. Technical report (2018).
  13. 13.
    Pelechrinis, K., Papalexakis, E., Faloutsos, C.: SportsNetRank: network-based sports team ranking. In: ACM SIGKDD Workshop on Large Scale Sports Analytics (2016)Google Scholar
  14. 14.
    Peña, J., Touchette, H.: A network theory analysis of football strategies. In: Clanet, C. (ed.), Sports Physics: Proceedings of 2012 Euromech Physics of Sports Conference, pp. 517–528, Editions de l’Ecole Polytechnique, Palaiseau (2013). ISBN: 978-2-7302-1615-9Google Scholar
  15. 15.
    Rosenbaum, D.: Measuring how NBA players help their teams win (2004). Accessed 5 June 2018
  16. 16.
    Seidl, T., Cherukumudi, A., Hartnett, A., Carr, P., Lucey, P.: Bhostgusters: realtime interactive play sketching with synthesized NBA defenses (2018)Google Scholar
  17. 17.
    Skinner, B.: The price of anarchy in basketball. J. Quant. Anal. Sports 6(1), 3 (2010)MathSciNetGoogle Scholar
  18. 18.
    Winston, W.L.: Mathletics: How Gamblers, Managers, and Sports Enthusiasts Use Mathematics in Baseball, Basketball, and Football. Princeton University Press, Princeton (2012)zbMATHGoogle Scholar
  19. 19.
    Zhan, E., Zheng, S., Yue, Y., Lucey, P.: Generative multi-agent behavioral cloning. arXiv preprint arXiv:1803.07612 (2018)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of PittsburghPittsburghUSA

Personalised recommendations