Query- and Candidate-Aware Long User Sequence Modeling for Sponsored Product Ranking in Search
Organizations: Wayfair LLC, USA
Abstract
User sequence modeling is widely used in recommendation and advertising. Search ranking presents an additional challenge: the current query expresses immediate intent, while a candidate product determines which parts of a user's long-term history are relevant. We present a production sequence framework for sponsored-product ranking that augments recent behavior with two retrieval channels over long-term history: candidate-nearest-neighbor retrieval and query-nearest-neighbor retrieval. The selected actions are encoded together with dedicated query and candidate context tokens, while candidate-aware early fusion injects the candidate into every history token. Offline ablations show that dual retrieval improves major ranking metrics relative to the production baseline. In an online A/B test on sponsored-product search traffic, the model increased CTR, attributed conversion rate, and orders per impression.
Figures & tables
| ID | Retrieval history | Early fusion | NAL | |
| baseline | Recent only | Off | On | Off |
| M0 | Recent only | On | On | On |
| M1 | Recent + candidate-NN | On | On | On |
| M2 | Recent + query-NN | On | On | On |
| M3 | Recent + candidate-NN + query-NN | On | On | On |
| M4 | Recent + candidate-NN + query-NN | Off | On | On |
| ID | Click AUC (%) | Order-7d AUC (%) |
| baseline | – | – |
| M0 | +0.46 | -0.61 |
| M1 | +1.16 | +1.35 |
| M2 | +1.00 | +1.16 |
| M3 | +1.37 | +2.19 |
| M4 | +0.45 | +0.28 |
| Metric | Relative change (%) | Significant at |
| CTR | +6.0 | Yes |
| CPC | -1.3 | Yes |
| Ad spend | +0.8 | Yes |
| Orders / impression | +11.5 | Yes |
| Attributed CVR | +5.2 | Yes |
Sequence Modeling
Sequence modeling studies how to represent, predict, classify, and generate ordered data such as text, time series, events, and biological sequences.
See all 268 papers