Method
Deep & Cross Network
Network with explicit feature-cross layers (DCN, DCNv2).
21 cases from 10 companies apply Deep & Cross Network. 16 were checked in an online A/B test; 3 report results in production.
Typical tasks: Rank search results, Retrieve and rank from millions of items, Recommend from what the user just did, Reduce ML cost and 5 more. Companies: Pinterest, Avito, Etsy, DoorDash, Snap, Thumbtack and 4 more. Often combined with: Multi-task learning, Two-tower model, Gradient boosting, Sequential recommendation, Platt scaling and 44 more.
