This year marks the 101st anniversary of the world’s largest annual sporting event, “Le Tour de France.”  The three-week competition attracts a worldwide television audience of 3.5 billion people, has an entire budget of more than €100 million, and covers approximately 2,500 kms in total. Unlike any other sport, the cyclists ride in the competition for five to seven hours each day for three consecutive weeks with only two rest days.

Due to high intensity training regimes and the sheer length of cycling competitions, the sport is rife with doping offenses – especially during “le Tour,” as Lance Armstrong has infamously set the precedence for. The need to recover quickly is absolutely paramount to the success of the competitor, and drugs are a tempting means of ensuring that recovery. However, big data is offering an alternative to help performance maximization.

Extensive data analysis is now being conducted on everything from cycling equipment, training routines, diet and supplements. “If you want to improve physical performance,” says Bastian Döhling, coach at Athelete Lab, “quantifying your training is the only way. If you can measure your performance you can improve it.”

Indeed, during the London Olympics, data analysis on cyclers took on a whole new form. Sky Christopherson, the Women’s 2012 U.S. Olympic Cycling Team Trainer, explained, for example, that on top of capturing data on the best diet and training regimes, he would also look at minute details like sleep cycles, circadian rhythms, continuous blood sugar levels, blood biomarkers like Vitamin D, and hormone levels. In fact, when the team arrived in London, their rooms would have their temperature adjusted so that the amount of deep sleep they experienced increased. Ultimately, adjustments such as these ended up making the difference between winning and losing.

“We saw in the data that early morning sun exposure … not just on the skin for Vitamin D synthesis, but actually in the eyes…was kind of anchoring biorhythms, and that was related to sleep latency and quality, which improved recovery,” Christopherson recalled.

The results of these extensive data analytics were remarkable – before the Olympics, the U.S. team were 5 seconds away from not being considered for the medals, but ended up with a Silver in the actual competition.


The Perfect Athlete from Duncan Elms on Vimeo.
And as Chris Froome proved in the 2013 Tour de France, big data can not only help improve performance, but serve as evidence against or for doping allegations. Before going on to win the tournament, Froome was repeatedly faced with questions about whether his superior performance was drug-enhanced. Froome’s Team Sky responded to these inquiries by releasing two years of data mapping Froome’s “physical power output,” proving that he was indeed capable of the feats he was accomplishing without any assistance. The proof, in other words, was quite literally in the numbers – a test that could weed out other cyclists with similar allegations but without the statistical backing.

Whether by maximizing performance, or substantiating a cyclist’s clean record, big data has the capacity to play a defining role in this year’s tournament and in cycling at large. As Chris Murphy of Information Week notes, “Teams track power data – measured basically by the watts a person generates to pedal a bike versus a person’s weight,” so the sport already has a history of maintaining a comprehensive dataset. Now the question is whether the US Women’s Cycling Team’s success and Froome’s innovative response to drug allegations will have wider implications in years to come for Tour de France competitors.

Interested in more content like this? Sign up to our newsletter, and you wont miss a thing!

(Image Credit: Wayne England)

Previous post

Machine Learning and the Big Data Ecosystem, with Adam Drake

Next post

Synapsify Gets $85k to Become Your Virtual Analyst