Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks

Abstract

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.

Accepted by AAAI 2014

Cited by in corpus (16)

• Click-Through Rate Prediction in Online Advertising: A Literature Review
• MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation
• Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction
• Deep Character-Level Click-Through Rate Prediction for Sponsored Search
• Self-Supervised Graph Co-Training for Session-based Recommendation
• Learning to Recommend via Meta Parameter Partition
• Time-Aware Prospective Modeling of Users for Online Display Advertising
• Sequential Search with Off-Policy Reinforcement Learning
• Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
• Surveys without Questions: A Reinforcement Learning Approach
• Modeling Dyadic Conversations for Personality Inference
• Location Prediction via Bi-direction Speculation and Dual-level Association
• Click-Through Rate Prediction with the User Memory Network
• An Enhanced Ad Event-Prediction Method Based on Feature Engineering
• Learning Preferences and Demands in Visual Recommendation
• Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading