Analyzing cycling sensors data through ordinal logistic regression with functional covariates

International audienceWith the emergence of numerical sensors in sports, all cyclists can now measure many parameters during their effort, such as the speed, the slope, the altitude, their heart rate or their pedaling cadence. The present work studies the effect of these parameters on the average developed power, which is the best indicator of the cyclist performance. For this, a cumulative logistic model for ordinal response with functional covariate is proposed. This model is shown to outperform the competitors on a benchmark study, and its application on cyclist data confirms that the pedaling cadence is a key performance indicator. But maintaining a high cadence during long effort is a typical characteristic of high level cyclists, which is something on which amateur cyclists can work on to increase their performance