Graph Intention Network for Click-through Rate Prediction in Sponsored Search
This addresses CTR prediction for sponsored search platforms, improving user experience and revenue, but it is incremental as it builds on existing deep learning models with graph-based enhancements.
The paper tackles the behavior sparsity and weak generalization problems in click-through rate prediction for sponsored search by proposing a Graph Intention Network (GIN) that uses a co-occurrence commodity graph with multi-layered graph diffusion, achieving significant CTR improvements in offline and online tests on real-world e-commerce data.
Estimating click-through rate (CTR) accurately has an essential impact on improving user experience and revenue in sponsored search. For CTR prediction model, it is necessary to make out user real-time search intention. Most of the current work is to mine their intentions based on user real-time behaviors. However, it is difficult to capture the intention when user behaviors are sparse, causing the behavior sparsity problem. Moreover, it is difficult for user to jump out of their specific historical behaviors for possible interest exploration, namely weak generalization problem. We propose a new approach Graph Intention Network (GIN) based on co-occurrence commodity graph to mine user intention. By adopting multi-layered graph diffusion, GIN enriches user behaviors to solve the behavior sparsity problem. By introducing co-occurrence relationship of commodities to explore the potential preferences, the weak generalization problem is also alleviated. To the best of our knowledge, the GIN method is the first to introduce graph learning for user intention mining in CTR prediction and propose end-to-end joint training of graph learning and CTR prediction tasks in sponsored search. At present, GIN has achieved excellent offline results on the real-world data of the e-commerce platform outperforming existing deep learning models, and has been running stable tests online and achieved significant CTR improvements.