Manuscript received February 10, 2023; revised April 10, 2023; accepted June 14, 2023.
Abstract—Finding and acquiring promising talent has always been one of the most important management issues in various organizations. In professional sports, this activity is referred to as scouting. For a long time, it was left to the intuition and experience of individuals. To make scouting more rational, it is important to quantitatively evaluate the skills of potential players. Traditional methods of evaluating player ability have focused on assessing the individual, but another approach is possible that evaluates player ability while considering compatibility with other players. In this study, we developed a sports player ability estimation method for basketball that considers compatibility between players by using Factorization Machines, which are machine learning models mainly used in recommendation systems and known for their superiority in extracting interactions between elements. In addition, we proposed a player scouting framework based on our developed method. Experiments based on professional basketball leagues showed that the proposed framework can estimate abilities more realistically than existing methods and has effective properties for scouting players. The widespread use of the system based on the proposed framework is expected to improve the efficiency of scouting, increase the liquidity of the player market, and reduce the mismatch between teams and players, thereby increasing the level of competition and revitalizing the professional sports industry.
Index Terms—Sports Analytics, Factorization Machines, Basketball
H. Tashiro is with Graduate School of Engineering, The University of Tokyo, Japan (e-mail: tashiro@torilab.net).
M. Nishiguchi is with Graduate School of Engineering, The University of Tokyo, Japan (e-mail: nishiguchi.mao@mail.u-tokyo.ac.jp).
T. Shimano is with SportMeme, inc, Japan (e-mail: t.shimano.55@sportmeme.co).
K. Morikawa is with SportMeme, inc, Japan (e-mail: morikawa.kenta.mystery@gmail.com).
R. Nagano is with SportMeme, inc, Japan (e-mail: r.nagano.47@sportmeme.co).
F. Toriumi is with Graduate School of Engineering, The University of Tokyo, Japan (e-mail: tori@sys.t.u-tokyo.ac.jp).
*Correspondence: tashiro@torilab.net
[PDF]
Cite: Haruhiko Tashiro, Mao Nishiguchi, Takuya Shimano, Kenta Morikawa, Ryota Nagano, Fujio Toriumi, "Basketball Scouting Framework Considering Interaction among Players," International Journal of Knowledge Engineering vol. 9, no. 2, pp. 36-42, 2023.
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (
CC BY 4.0).
