Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Object/Recommend System/Recommender Satisfaction/
Recommender System Deployment
Search

Recommender System Deployment

Creator
Creator
Seonglae Cho
Created
Created
2025 Mar 5 13:8
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Mar 5 13:17
Refs
Refs
Slide credits: James (Netflix), Praveen (Spotify)
Slide credits: James (Netflix), Praveen (Spotify)
Need good offline and check online correlation

Consideration

  • Production recommender and test recommender’s logged feedback might different
    • Special logged data need to be collected through randomized data or log propensity scores
    • Counterfactual evaluation → off-policy evaluation
 
 
 
 
Offline Evaluation to Make Decisions About PlaylistRecommendation Algorithms - Spotify Research
Spotify’s official research blog
Offline Evaluation to Make Decisions About PlaylistRecommendation Algorithms - Spotify Research
https://research.atspotify.com/publications/offline-evaluation-to-make-decisions-about-playlistrecommendation-algorithms/
Offline comparative evaluation with incremental, minimally-invasive online feedback - Spotify Research
Spotify’s official research blog
Offline comparative evaluation with incremental, minimally-invasive online feedback - Spotify Research
https://research.atspotify.com/publications/offline-comparative-evaluation-with-incremental-minimally-invasive-online-feedback/
Estimating clickthrough bias in the cascade model - Spotify Research
Spotify’s official research blog
Estimating clickthrough bias in the cascade model - Spotify Research
https://research.atspotify.com/publications/estimating-clickthrough-bias-in-the-cascade-model/
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Object/Recommend System/Recommender Satisfaction/
Recommender System Deployment
Copyright Seonglae Cho