Support Questions

Find answers, ask questions, and share your expertise
Announcements
Celebrating as our community reaches 100,000 members! Thank you!

USER and ITEM groups: How best to handle in Oryx

avatar
New Contributor

On a multi national website our users access the site with a given locale (en-GB, en-US, etc) Locale of a user may effect items in two different ways. 1) An Item cannot be associated with  certain locales (for legal or availability). Items may mean different things to users in different locales (trip to paris is a weekend city break to en-GB but a family holiday for two weeks to en-US)

 

I was thinking along the lines of using locale as a tag with a very strong confidence value but i'm now thinking is that good enough ?

 

Should I compute and serve multiple locale based models ? Has anyone solved a similiar issue before (I'm thinking this is not a new use-case

 

Lee C

1 ACCEPTED SOLUTION

avatar
Master Collaborator
Hard filtering rules need to be implemented in a RescorerProvider, or in logic on the caller side. Tagging users and items with a locale could make sense. It would function as a soft filter nudging people towards things in the same locale. That could be useful as well, but is a different thing from implementing business rules. If your items and users are nearly completely disjoint by locale (e.g. very few items are available in multiple locales and very few users shop in multiple locales) then separate models might be the best way to go. No filtering logic needed although you then manage a model per locale. But the models are smaller and easier to handle. If there is moderate overlap, then a unified model can benefit from the cross-locale learning.

View solution in original post

1 REPLY 1

avatar
Master Collaborator
Hard filtering rules need to be implemented in a RescorerProvider, or in logic on the caller side. Tagging users and items with a locale could make sense. It would function as a soft filter nudging people towards things in the same locale. That could be useful as well, but is a different thing from implementing business rules. If your items and users are nearly completely disjoint by locale (e.g. very few items are available in multiple locales and very few users shop in multiple locales) then separate models might be the best way to go. No filtering logic needed although you then manage a model per locale. But the models are smaller and easier to handle. If there is moderate overlap, then a unified model can benefit from the cross-locale learning.