Visualize the athlete data to create an understanding of the athletes' skills and profile. Find the optimal run time and time gates before the athlete even needs to put on their skis.
Swissski is the National Ski Federation and develops Swiss Wintersport Athletes in eleven different disciplines.
- Björn Bruhin - Scientific Assistant Swissski
- Marco Bäschlin - CEO Force8 AG
Our solution is an interactive dashboard which allows the user to analyse the provided data. It includes a track visualization, showing the time and speed of a specific athlete for a specific run, a correlation matrix which can dynamically be adjusted, a t-sne clustering analysis, a descriptive data analysis and a regression model with adjustable input parameters. The regression model is a multivariate linear regression and the parameter analysis was done with a Random forest regressor. All the code is provided to the challenge owner and can be expanded with additional data.
The goal was to identify the most important parameters for athletes to improve their run. We approached this by analysing the data, aggregated as well as raw data, ran initial clustering methods and basic ML algorithms. As the dataset was at points inconsistent or incomplete, it was difficult to fit accurate ML models. However, we created insightful data visualizations and implemented basic ML models to find the most important parameters.
Potential next steps
- Record more data and create higher accuracy for ML models
- Improve the Dashboard
- Run more sophisticated algorithms, i.e. Neural Networks
Swisski has collected the data of several athletes runs at several courses, including time gates, turn velocities and slalom angles.