Deeply Supervised Model for Click-Through Rate Prediction in Sponsored Search

January 1, 2019

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, limiting their 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.

Download

Publication Type

Paper

Conference / Journal Name

Data Mining and Knowledge Discovery

Authors

BibTeX


@inproceedings{
    author = {},
    title = {‌Deeply Supervised Model for Click-Through Rate Prediction in Sponsored Search‌},
    booktitle = {Proceedings of Data Mining and Knowledge Discovery‌},
    year = {‌2019‌}
}