Bike2Vec: Vector Embedding Representations of Road Cycling Riders and Races

TL;DR

This paper introduces a novel method for creating vector embeddings of cyclists and races using historical data, enabling improved analysis and prediction in professional road cycling.

Contribution

The paper presents a new unsupervised learning approach to generate embeddings for riders and races, capturing meaningful features for cycling analytics.

Findings

Embeddings effectively represent rider and race characteristics.

Embeddings can be used for predicting race outcomes.

The method captures interesting features of cycling data.

Abstract

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.