Riduck utilizes machine learning and generative statistical models to provide precise estimations of cycling metrics such as FTP, VO2MAX, and FATMAX, enabling users to optimize their training plans. By analyzing wearable data, Riduck delivers tailored coaching that simplifies the interpretation of exercise types and effects, enhancing training efficiency for cyclists.
Funding
Funding not disclosed
Founders
Product
Problem
Cyclists often struggle to accurately gauge their fitness metrics like FTP, VO2MAX, and FATMAX, hindering their ability to create effective and personalized training plans. Interpreting complex data from wearables can be time-consuming and require specialized knowledge, making it difficult for cyclists to optimize their performance.
Solution
Riduck leverages machine learning and generative statistical models to provide cyclists with precise estimations of key performance indicators. By analyzing data from wearable devices, Riduck simplifies the interpretation of exercise types and their effects, delivering tailored coaching insights. The platform identifies the type and effect of any exercise, allowing users to understand the impact of different training methods. Riduck also enables cyclists to find and compete with similarly skilled rivals worldwide, fostering motivation and engagement.
Target Audience
Riduck is designed for cyclists of all levels who want to optimize their training and performance through data-driven insights and personalized coaching.
Features
- Machine learning-driven estimation of FTP (Functional Threshold Power), VO2MAX, and FATMAX
- Personalized AI coaching based on wearable data analysis
- Automatic interpretation of exercise types and their effects (e.g., interval training, tempo rides)
- Global competitor matching based on skill level
- Integration with Strava
- "Animal Metrics" providing intuitive visualizations of training zones (e.g., Tiger for Tabata, Leopard for HIIT)