Predicting biathlon shooting performance using machine learning

Mar 23, 2018Journal of sports sciences

Using machine learning to predict biathlon shooting performance

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

Analysis of 118,300 shots revealed lower hit rates in sprint and pursuit disciplines compared to individual and mass start events.

Hit rates were significantly lower in standing shooting compared to prone shooting.
The 1 prone and 5 standing shots also showed reduced hit rates.
A tree-based boosting model predicted future shots with an area under the ROC curve of 0.62.
The primary predictor of shooting performance was an athlete's previous mode-specific hit rate.
Despite complex modeling, a high degree of randomness in shooting outcomes remained.

AI simplified

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 1prone and 5standing 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. st th

Full Text

Full text is available at the source.

View full text ↗

Predicting biathlon shooting performance using machine learning

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief