<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In baseball, every play on the field is quantitatively evaluated and the statistics have an effect on individual and team strategies. The weighted on base average (wOBA) is well known as a measure of a batter’s hitting contribution. However, this measure ignores the game situation, such as the runners on base, which coaches and batters are known to consider when employing multiple hitting strategies, yet, the effectiveness of these strategies is unknown. This is probably because (1) we cannot obtain the batter’s strategy and (2) it is difficult to estimate the effect of the strategies. Here, we propose a new method for estimating the effect using counterfactual batting simulation. The entire framework consists of two phases: (i) generate a counter-factual batter’s ability based on their actual performances and (ii) simulate games with the batting simulator. To realize (i), we propose a deep learning model that transforms batting ability when batting strategy is changed. This method can estimate the effects of various strategies, which has been traditionally difficult with actual game data. We found that, when the switching cost of batting strategies can be ignored, the use of different strategies increased runs. When the switching cost is considered, the conditions for increasing runs were limited. Our results suggest that players and coaches should be careful when employing multiple batting strategies given the trade-offs thereof. We also discuss practical baseball use-cases to use this simulation.</p>
</abstract>

In baseball, every play on the field is quantitatively evaluated and the statistics have an effect on individual and team strategies. The weighted on base average (wOBA) is well known as a measure of a batter’s hitting contribution. However, this measure ignores the game situation, such as the runners on base, which coaches and batters are known to consider when employing multiple hitting strategies, yet, the effectiveness of these strategies is unknown. This is probably because (1) we cannot obtain the batter’s strategy and (2) it is difficult to estimate the effect of the strategies. Here, we propose a new method for estimating the effect using counterfactual batting simulation. The entire framework consists of two phases: (i) generate a counter-factual batter’s ability based on their actual performances and (ii) simulate games with the batting simulator. To realize (i), we propose a deep learning model that transforms batting ability when batting strategy is changed. This method can estimate the effects of various strategies, which has been traditionally difficult with actual game data. We found that, when the switching cost of batting strategies can be ignored, the use of different strategies increased runs. When the switching cost is considered, the conditions for increasing runs were limited. Our results suggest that players and coaches should be careful when employing multiple batting strategies given the trade-offs thereof. We also discuss practical baseball use-cases to use this simulation.

Estimating the effect of hitting strategies in baseball using counterfactual virtual simulation with deep learning

International Journal of Computer Science in Sport

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

In baseball, every play on the field is quantitatively evaluated and the statistics have an effect on individual and team strategies. The weighted on base...

Estimating the effect of hitting strategies in baseball using counterfactual virtual simulation with deep learning

Publié en ligne: 17 janv. 2023

Pages: 1 - 12

DOI: https://doi.org/10.2478/ijcss-2023-0001

Mots clés
BASEBALL, SIMULATION, MACHINE LEARNING, COUNTERFACTUAL

© 2023 Hiroshi Nakahara et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Estimating the effect of hitting strategies in baseball using counterfactual virtual simulation with deep learning

Publié en ligne: 17 janv. 2023

Pages: 1 - 12

DOI: https://doi.org/10.2478/ijcss-2023-0001

Mots clésBASEBALL, SIMULATION, MACHINE LEARNING, COUNTERFACTUAL

© 2023 Hiroshi Nakahara et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Mots clés
BASEBALL, SIMULATION, MACHINE LEARNING, COUNTERFACTUAL