Predicting biathlon shooting performance using machine learning

Maier, Thomas; Meister, Daniel; Trösch, Severin; Wehrlin, Jon Peter (2018). Predicting biathlon shooting performance using machine learning Journal of Sports Sciences, 36(20), pp. 2333-2339. Taylor & Francis 10.1080/02640414.2018.1455261

Text Maier_2018_Predicting biathlon shooting performance using machine learning.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (1MB) | Request a copy

Shooting in biathlon competitions substantially influences final rankings, but the predictability of hits and misses is unknown. The aims of the current study were A) to explore factors influencing biathlon shooting performance and B) to predict future hits and misses. We explored data from 118,300 shots from 4 seasons and trained various machine learning models before predicting 34,340 future shots (in the subsequent season). A) Lower hit rates were discovered in the sprint and pursuit disciplines compared to individual and mass start (P < 0.01, h = 0.14), in standing compared to prone shooting (P < 0.01, h = 0.15) and in the 1st prone and 5th standing shot (P < 0.01, h = 0.08 and P < 0.05, h = 0.05). B) A tree-based boosting model predicted future shots with an area under the ROC curve of 0.62, 95% CI [0.60, 0.63], slightly outperforming a simple logistic regression model and an artificial neural network (P < 0.01). The dominant predictor was an athlete’s preceding mode-specific hit rate, but a high degree of randomness persisted, which complex models could not substantially reduce. Athletes should focus on overall mode-specific hit rates which epitomise shooting skill, while other influences seem minor.

Item Type:	Journal Article (Original Article)
Division/Institute:	Swiss Federal Institute of Sports Magglingen SFISM > EHSM - Leistungssport > Sportphysiologie Ausdauer
Name:	Maier, Thomas; Meister, Daniel; Trösch, Severin and Wehrlin, Jon Peter
ISSN:	0264-0414
Publisher:	Taylor & Francis
Language:	English
Submitter:	Service Account
Date Deposited:	09 Dec 2020 12:55
Last Modified:	11 Jul 2023 11:41
Publisher DOI:	10.1080/02640414.2018.1455261
Related URLs:	Publication
PubMed ID:	29565223
Uncontrolled Keywords:	Sport competition modelling Leistungssport Ausdauer
ARBOR DOI:	10.24451/arbor.11012
URI:	https://arbor.bfh.ch/id/eprint/11012