Saved in:
Bibliographic Details
Main Authors: Baron, Ethan, Janssens, Bram, Bogaert, Matthias
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.10471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929278449352704
author Baron, Ethan
Janssens, Bram
Bogaert, Matthias
author_facet Baron, Ethan
Janssens, Bram
Bogaert, Matthias
contents Vector embeddings have been successfully applied in several domains to obtain effective representations of non-numeric data which can then be used in various downstream tasks. We present a novel application of vector embeddings in professional road cycling by demonstrating a method to learn representations for riders and races based on historical results. We use unsupervised learning techniques to validate that the resultant embeddings capture interesting features of riders and races. These embeddings could be used for downstream prediction tasks such as early talent identification and race outcome prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2305_10471
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bike2Vec: Vector Embedding Representations of Road Cycling Riders and Races
Baron, Ethan
Janssens, Bram
Bogaert, Matthias
Machine Learning
Vector embeddings have been successfully applied in several domains to obtain effective representations of non-numeric data which can then be used in various downstream tasks. We present a novel application of vector embeddings in professional road cycling by demonstrating a method to learn representations for riders and races based on historical results. We use unsupervised learning techniques to validate that the resultant embeddings capture interesting features of riders and races. These embeddings could be used for downstream prediction tasks such as early talent identification and race outcome prediction.
title Bike2Vec: Vector Embedding Representations of Road Cycling Riders and Races
topic Machine Learning
url https://arxiv.org/abs/2305.10471