Super excited to start laying down some advanced features to enhance your Strava experience. The key to any good AI is the data so over the next 6-8 weeks we’re enriching our data to unlock exciting new algorithms that we
Reimagining Strava Sync Process
Due to our steady growth we now need to be conscious of how much burden we’re putting on Strava’s servers as they rate limit apps to 600 hits / 15 minutes and 30K hits / day. Our original sync logic
Tagline
Things are starting to come together for a final push to get to ~1K users in the beta where we’ll lock down and drive a focus on testing and tuning production scale infrastructure. With this in mind we’d like your
Masimo Mighty Sat
I’m very excited to receive my Masimo Mighty Sat Pulse Oximeter tomorrow! I’ve been reading how a handful of professional triathletes have incorporated pulse oxygen data into their training. It’s intuitively obvious that the amount of oxygen in your blood will impact
Bike Prediction
As we head to the end of our 4rd month of beta usage I’m more than a bit disappointed at how accurate the bike prediction feature has been working. If you recall, we added a second algorithm in January in
Athlete Clusters
One of the initial visions for strive.ai was to offer features that help athletes find training partners with similar characteristics. We tried one approach in the early beta that clustered athletes based on starred segment completion time. This approach had “mixed
Improved Factors and Trends
We’ve been hard at work for the past 2 weeks refactoring our Factors and Trends features. Our mission is to continue to provide great visualizations and insights from your data!
Run Power and Best Efforts
Today we introduced improved support for runners in strive.ai we eluded to here. We’ve made the following changes: Removed the Run Pace threshold type Introduced Pace Best Efforts for 400, 800, 1600, 5K and 10K distances (aged over 8 weeks
Anomalies
Reader beware, this is a nerd post! One of the most common types of machine learning is used to detect outliers in a dataset. Today we introduced several “anomaly detection” algorithms into the beta that assess your activities, power thresholds and segment efforts. Why do we do
Support for Runners
Admittedly, we’ve started out with a focus on cycling with power. We attempted to mix in run pace thresholds using the same time duration concept [1, 5, 20, 60] as we do for heart rate and power. We learned