Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
This addresses click prediction for sponsored search systems, offering a novel approach that captures user behavior dependencies, though it is incremental in applying RNNs to this domain.
The paper tackles the problem of click prediction in sponsored search by modeling user sequential behavior with Recurrent Neural Networks, resulting in significant accuracy improvements over sequence-independent methods as demonstrated in large-scale evaluations.
Click prediction is one of the fundamental problems in sponsored search. Most of existing studies took advantage of machine learning approaches to predict ad click for each event of ad view independently. However, as observed in the real-world sponsored search system, user's behaviors on ads yield high dependency on how the user behaved along with the past time, especially in terms of what queries she submitted, what ads she clicked or ignored, and how long she spent on the landing pages of clicked ads, etc. Inspired by these observations, we introduce a novel framework based on Recurrent Neural Networks (RNN). Compared to traditional methods, this framework directly models the dependency on user's sequential behaviors into the click prediction process through the recurrent structure in RNN. Large scale evaluations on the click-through logs from a commercial search engine demonstrate that our approach can significantly improve the click prediction accuracy, compared to sequence-independent approaches.