Salvato in:
Dettagli Bibliografici
Autori principali: Baron, Ethan, Hau, Victor, Weng, Zeke
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.02343
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916472790450176
author Baron, Ethan
Hau, Victor
Weng, Zeke
author_facet Baron, Ethan
Hau, Victor
Weng, Zeke
contents Using data from professional bouldering competitions from 2008 to 2022, we train a logistic regression to predict climber results and measure climber skill. However, this approach is limited, as a single numeric coefficient per climber cannot adequately capture the intricacies of climbers' varying strengths and weaknesses in different boulder problems. For example, some climbers might prefer more static, technical routes while other climbers may specialize in powerful, dynamic problems. To this end, we apply Probabilistic Matrix Factorization (PMF), a framework commonly used in recommender systems, to represent the unique characteristics of climbers and problems with latent, multi-dimensional vectors. In this framework, a climber's performance on a given problem is predicted by taking the dot product of the corresponding climber vector and problem vectors. PMF effectively handles sparse datasets, such as our dataset where only a subset of climbers attempt each particular problem, by extrapolating patterns from similar climbers. We contrast the empirical performance of PMF to the logistic regression approach and investigate the multivariate representations produced by PMF to gain insights into climber characteristics. Our results show that the multivariate PMF representations improve predictive performance of professional bouldering competitions by capturing both the overall strength of climbers and their specialized skill sets. We provide our code open-source at https://github.com/baronet2/boulder2vec.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02343
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boulder2Vec: Modeling Climber Performances in Professional Bouldering Competitions
Baron, Ethan
Hau, Victor
Weng, Zeke
Machine Learning
Using data from professional bouldering competitions from 2008 to 2022, we train a logistic regression to predict climber results and measure climber skill. However, this approach is limited, as a single numeric coefficient per climber cannot adequately capture the intricacies of climbers' varying strengths and weaknesses in different boulder problems. For example, some climbers might prefer more static, technical routes while other climbers may specialize in powerful, dynamic problems. To this end, we apply Probabilistic Matrix Factorization (PMF), a framework commonly used in recommender systems, to represent the unique characteristics of climbers and problems with latent, multi-dimensional vectors. In this framework, a climber's performance on a given problem is predicted by taking the dot product of the corresponding climber vector and problem vectors. PMF effectively handles sparse datasets, such as our dataset where only a subset of climbers attempt each particular problem, by extrapolating patterns from similar climbers. We contrast the empirical performance of PMF to the logistic regression approach and investigate the multivariate representations produced by PMF to gain insights into climber characteristics. Our results show that the multivariate PMF representations improve predictive performance of professional bouldering competitions by capturing both the overall strength of climbers and their specialized skill sets. We provide our code open-source at https://github.com/baronet2/boulder2vec.
title Boulder2Vec: Modeling Climber Performances in Professional Bouldering Competitions
topic Machine Learning
url https://arxiv.org/abs/2411.02343