Does a Personalize model need re-training before a new user's attributes are reflected in filtering?
I'm considering using the User-Personalization recipe with the new PutItems and PutUsers APIs, but with requirements on making sure that new users whose metadata is known receive only appropriate recommendations.
For example after initial sign-up a user's country/age/membership status/etc are known and may be posted to Personalize PutUsers...
As I understand the filtering mechanism is quite separate from the personalization model, but then I think in the past I heard of some differences between how new users and new items get picked up in modelling.
Will new users' attributes be reflected in recommendation filters straight away (after the typical <15min near-real-time delay as for new/updated items?)
Or would new users continue to receive out-of-filter recommendations until the next model re-train? Maybe even until the next FULL model re-train, if an UPDATE training is not sufficient to onboard new users?
- Neueste
- Die meisten Stimmen
- Die meisten Kommentare
Regarding filters: they are working directly with a datasets data, so if you use PutUsers API call to add a new user (update existing user) then in max 15 minutes (typically less) filters will use this data to filter recommendations for this new user. This apply to all datasets (items and interaction as well).
New user will also get a personalised experience after several clicks if you will implement event tracker (recommendations will be shifted to his interest based on a current model). FULL mode (retraining) will help to learn insights from a user interactions for a future use.
Relevanter Inhalt
AWS OFFICIALAktualisiert vor 2 Jahren