Background

At the beginning of 2020, as soon as the season started, I found myself checking the list of registered competitors and categories and thinking: How can I increase my chances of having a good result? I didn’t know any of the competitors and teams. Basically, all I could do was to conduct a course recon and trust my physical conditioning.

Of course, I didn’t stop thinking about it, and in no time, I was checking each contestant’s name and searching for their information. I then discovered that USA Cycling (The American governing body for bicycle racing) has a history of all races and athletes, including amateurs and professionals. Bingo!

Learn more about the background and how I developed this project on this article.

---

Data

The data is gathered from Zwift, including race lists, registered riders, categories, routes, distance, and elevation information.

I used ZwiftPower.com to collect historical data on each rider. Information such as weight, age, FTP, among others, were consolidated in a final list of the field for further analysis.

Route images are collected from ZwiftHacks.com

---

Prediction Model

I am currently using machine learning and regression algorithms for the prediction model. To learn more about the prediction model, check my article about this project on this link.

---

The App

This is a non-profit and open-source project. It was developed for academic and research purposes, using R language, Shiny framework, Shinydashboard, Caret, and others packages. Soon the link to the project's source on GitHub will be available. Collaboration for improvement will be more than welcome. License: GNU GPLv3

---

Author