Core Features

  1. Peak thresholds for bike power, run power and heart rate trended over time.  Each activity is analyzed to determine the peak thresholds.  The thresholds from each activity are stack ranked against the last 8 weeks to determine if you have an achievement 1, 2 or 3 with 1 meaning a breakthrough. We capture all the available context (e.g. cadence, temp, altitude, velocity, gradient, etc) from each peak threshold to support the Threshold Factors algorithm mentioned below.
  2. Run Best Efforts for 400m, 800m, 1600m, 5,000m and 10,000m.  We record the pace in meters / second and context for you hitting the peak pace for all of your run activities.
  3. Segment Effort Watts/kg achievements and leaderboards.  Pivots Strava’s PR from time to watts/kg using your weight and power from power meter.  This feature is only active for Rides and Virtual Rides done with a power meter when your weight has been configured in Strava.
  4. Compute and maintain a trend of the typical Cycling Power Metrics (Normalized Power, Intensity Factor and Training Stress Score)
  5. Threshold Factors: Leverage data science to advise users which variables are having the largest positive or negative impact on their peak thresholds.  For example, what 7 variables are impacting your 1 minute bike power?
  6. Best Effort Factors:  Like Threshold Factors, we assess the variables in relation to a target and show you which variables have the largest impact on the outcome.
  7. Activity Predictions:  The following classification algorithms are live in the system:  ActivityType (used to decide if other predictions are appropriate), Bike (used to alert you if you may have forgotten to change bike from default).
  8. Athlete Finder:  This algorithm groups cyclist in each geo by watts/kg over 1, 5 and 20 minutes.  The goal of this feature is to help you find good training partners.
  9. Power Curve: We calculate a 60 minute power curve for each activity with power (bike and run).  In the activity view (mobile) we depict the activity vs. your prior 8 weeks power curve. We use this information to predict power you can generate in situations.  The curve is a sample of peak average power over every 5 seconds for the first minute and every minute for the remaining 59 minutes.
  10. Threshold Anomalies:  Alert you when pea thresholds seem inconsistent with your recent history in hopes of flagging situations where a sensor was reading high or low incorrectly.  We’ll be adding a flag option for you to exclude samples that are inaccurate.  One of our biggest ah-ha moments in strive.ai development is how frequently heart-rate and power peter readings are off.
  11. Segment Performance Factors: Calculate variables impacting Segment Performance (moving time) across all strive.ai efforts across a segment.  This feature brings the same “Factors” approach we do to your Peak Thresholds to each Strava Segment helping athletes understand what the keys to success for a top placement are on a particular segment leaderboard.
  12. Running Dynamics Factors:  Now that we have a Garmin Connect integration we can offer insight as to what running dynamics variables are impacting your run power or pace.
  13. Segment PR Predictions: Predict a wind assist metric, estimated speed (based on 8 week power curve) and required power for a Strava PR on 1..N starred segments using the integrated weather data..  Users can “watch” a starred segment and visualize the 3 predictions (wind, speed and power) in our mobile app.  The plan is to move to notifications as to when it’s a good day/time to hit a segment.
  14. Better Bike Classifier: Using the raw .fit files we’ve improve the accuracy of the Bike Classifier to detect which bike you’ve used on a Ride or Virtual Ride.  This algorithm is 100% accurate provided you’ve labeled your bikes properly in Strava.
  15. Best Effort Distance Thresholds: Like we do over time for cyclists we now offer over distance for runners on Run or Virtual Run activities.  The achievements are top 3 over the past 8 weeks for each distance (e.g. top 3 average power or heart-rate over 5K distance).

Roadmap Algorithms/Features 2018H1

  1. Weather Factors:  How does the weather forecast impact your heart-rate or run/bike power?
  2. Apple Health Kit integration: Bring in additional context data into strive.ai to improve performance factors insight.
  3. Android Mobile Client.  Once the Segment Performance and Garmin Connect Features are in the Apple App Store we’ll move to focus on the Android Mobile app.
  4. Best Effort Distance Threshold Factors: Determine top 7 variables impacting your 1600m run power.
  5. Moxy Muscle Oxygen Analytics
  6. Swimming Mechanics Analytics