Giving a scientific push to cyclists at the Tour de France
Writing a thesis can be a lot of fun, particularly when you choose a subject that’s related to your favourite hobby. For Kristian van Kuijk, an avid cyclist, it’s even led to a dream come true. He’s found an accurate way to predict the energy burned by a rider during a race. The algorithm has impressed Team Jumbo-Visma, who are using Kristian’s predictions in this month’s Tour de France.
Predicting the personal energy needs of a professional cyclist is not easy, given that the average Tour de France contender burns around 7000 calories during a Tour stage. Kristian van Kuijk has taken up the challenge and found a way. He is an ambitious student from the honours programme KE@Work of the Data Science and Artificial Intelligence bachelor’s programme at Maastricht University and a passionate cycling fan. For his thesis, he has built an algorithm that makes it possible to predict the energy consumption of cyclists.
These predictions are made through machine learning based on data such as the stage profile or the individual cyclist’s BMI. They also take account of much more unforeseen factors such as weather conditions or race tactics. Through KE@Work, Kristian got in touch with Team Jumbo–Visma, a leading Dutch professional bicycle racing team, where he put his AI model into practice. Jumbo-Visma nutritionists quickly became so enthusiastic about Kristian's predictions and his algorithm that they’re now using it on a daily basis. In fact, they have asked him if he would like to do the same for the women's team. And even after finishing this project, Kristian will continue to work at Visma.
