• Post Reply Bookmark Topic Watch Topic
  • New Topic
programming forums Java Mobile Certification Databases Caching Books Engineering Micro Controllers OS Languages Paradigms IDEs Build Tools Frameworks Application Servers Open Source This Site Careers Other Pie Elite all forums
this forum made possible by our volunteer staff, including ...
Marshals:
  • Campbell Ritchie
  • Ron McLeod
  • Paul Clapham
  • Jeanne Boyarsky
  • Liutauras Vilda
Sheriffs:
  • Rob Spoor
  • Bear Bibeault
  • Tim Cooke
Saloon Keepers:
  • Tim Moores
  • Stephan van Hulst
  • Tim Holloway
  • Carey Brown
  • Piet Souris
Bartenders:
  • Frits Walraven
  • Himai Minh

liveProject: Build an ML Recommender System - Dealing with changing user preferences?

 
Greenhorn
Posts: 5
  • Mark post as helpful
  • send pies
    Number of slices to send:
    Optional 'thank-you' note:
  • Quote
  • Report post to moderator
Hello!

On an e-commerce site, how do you deal with the issue of users' preferences that is regularly changing? Are there current approaches/algorithms to handle this?

Regards,
Andrea
 
Greenhorn
Posts: 9
  • Mark post as helpful
  • send pies
    Number of slices to send:
    Optional 'thank-you' note:
  • Quote
  • Report post to moderator
Hi Andrea,

If you have an e-commerce site the size or Amazon, then you should worry about changing tastes of the user. Mostly you will be trying to use as much of the data you have, because in most cases users will have very short transaction history. If you are in the lucky situation that there are so much data that changes in users' preferences can be measured, it would be worth looking into sequence based recommenders which predicts continuations of sequences.

If on the other hand you want to look at user profiles, I would recommend to have a look at the work they did at spotify: https://research.atspotify.com/finding-structure-in-users-evolving-listening-preferences/

Regards,
Kim
 
Consider Paul's rocket mass heater.
reply
    Bookmark Topic Watch Topic
  • New Topic