#strava

#strava

Strava is using "Machine Learning" (ML) models to help clean up logged riding errors, intentional or not. James, an engineer at Strava, explained in the post that the recent crackdowns were threefold. First, they introduced a new ML model, specifically aimed at catching e-bikes. This "Enhanced E-Bike Detection" flags and removes activities logged as a normal ride, but that were clearly recorded with electric assist.

Earlier this month, Strava, the popular fitness-tracking app, released its annual "Year in Sport" wrap-up-a cutesy, animated series of graphics summarizing each user's athletic achievements. But this year, for the first time, Strava made this feature available only to users with subscriptions ($80 per year), rather than making it free to everyone, as it had been historically since the review's debut in 2016.

"We are aware of an employee who exhibited extremely concerning off-hours behavior," the comment read. "We don't condone violence of any kind and this does not reflect the standards we expect of our team. This past Monday, we made the decision to end the individual's employment."

Behavioural data, smart logic, and curiosity-driven UX - this is what good survey design looks like.

Mateo Ortega, former VP of connected partnerships at Strava, remarked, "I don’t really think of Strava as a social network, although it’s marketed that way for athletes."