Method
CTR / feedback prediction
Predicting click, conversion or like probability (DCN, DeepFM, Wide&Deep).
46 cases from 17 companies apply CTR / feedback prediction. 26 were checked in an online A/B test; 14 report results in production. Includes variants: Deep & Cross Network, Wide & Deep.
Typical tasks: Retrieve and rank from millions of items, Recommend from what the user just did, Rank search results, Reduce ML cost and 14 more. Companies: Pinterest, Meta, Avito, LinkedIn, DoorDash, Instacart and 11 more. Often combined with: Deep & Cross Network, Multi-task learning, Sequential recommendation, Wide & Deep, Two-tower model and 80 more.


