Concept
Batch Offline Update
The traditional update mode of recommendation systems, in which the system periodically, from several hours to a day, retrains or updates the model with accumulated data and then pushes new ranking results to users. Latency is high, but computing resources are controllable.
Timeline (last 90 days)
Oct 13
Traditional recommender systems often adopt a batch offline update mode, where the system retrains or updates the model every few hours or even once a day, and user feedback often takes effect only the next day.
Unverified50%