The feed is treating an athlete’s last sport as a lasting preference.
Recent activity signals protect freshness, while longer training patterns protect relevance for multi-sport athletes.
Who you’d be doing this for
“I logged three runs this week and my feed is still full of cycling posts I skipped days ago.”
Chiamaka Osei · Recreational triathlete
She records runs, rides, and swims and relies on the feed to find activities from athletes with similar training patterns.
What is at stake
Recommendation saves fell from 5.5% to 4.1% for athletes switching between running and cycling. You have to weigh fresher activity signals against reliable feed latency.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- fresh activity signals vs durable training preferences
- recommendation relevance vs feed latency
- model improvement vs release-window certainty
Why Strava
Strava’s activity and community data make feed relevance part of how athletes return to share and discover workouts.
Written with these in mind
Not your kind of problem? 6 more at Strava, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.