Title | ||
---|---|---|
Deeply Supervised Semantic Model for Click-Through Rate Prediction in Sponsored Search. |
Abstract | ||
---|---|---|
In sponsored search it is critical to match ads that are relevant to a query and to accurately predict their likelihood of being clicked. Commercial search engines typically use machine learning models for both query-ad relevance matching and click-through-rate (CTR) prediction. However, matching models are based on the similarity between a query and an ad, ignoring the fact that a retrieved ad may not attract clicks, while click models rely on click history, being of limited use for new queries and ads. We propose a deeply supervised architecture that jointly learns the semantic embeddings of a query and an ad as well as their corresponding CTR.We also propose a novel cohort negative sampling technique for learning implicit negative signals. We trained the proposed architecture using one billion query-ad pairs from a major commercial web search engine. This architecture improves the best-performing baseline deep neural architectures by 2% of AUC for CTR prediction and by statistically significant 0.5% of NDCG for query-ad matching. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Information Retrieval | Web search engine,Learning to rank,Click-through rate,Architecture,Search engine,Information retrieval,Computer science,Sampling (statistics),Semantic data model |
DocType | Volume | Citations |
Journal | abs/1803.10739 | 0 |
PageRank | References | Authors |
0.34 | 21 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jelena Gligorijevic | 1 | 5 | 2.16 |
Djordje Gligorijevic | 2 | 19 | 6.55 |
Ivan Stojkovic | 3 | 0 | 0.34 |
Xiao Bai | 4 | 15 | 1.59 |
Amit Goyal | 5 | 44 | 13.24 |
Zoran Obradovic | 6 | 1110 | 137.41 |