I'm assuming that even though the recommendation system is 'offline', you're serving it to a user in some way that it can be tracked and desired outcomes of the recommendation are measured?
f
future-teacher-7046
01/26/2022, 4:12 PM
GrowthBook doesn't support experiments like that which use historical data instead of actually running against live users
f
fast-telephone-84882
01/26/2022, 7:01 PM
ML model is being trained offline then it is being served to the live users
f
fresh-football-47124
01/26/2022, 7:11 PM
as long as you can see which user saw which model, it's possible to use GrowthBook to determine the difference