DeepAI AI Chat
Log In Sign Up

CAN: Revisiting Feature Co-Action for Click-Through Rate Prediction

by   Guorui Zhou, et al.

Inspired by the success of deep learning, recent industrial Click-Through Rate (CTR) prediction models have made the transition from traditional shallow approaches to deep approaches. Deep Neural Networks (DNNs) are known for its ability to learn non-linear interactions from raw feature automatically, however, the non-linear feature interaction is learned in an implicit manner. The non-linear interaction may be hard to capture and explicitly model the co-action of raw feature is beneficial for CTR prediction. Co-action refers to the collective effects of features toward final prediction. In this paper, we argue that current CTR models do not fully explore the potential of feature co-action. We conduct experiments and show that the effect of feature co-action is underestimated seriously. Motivated by our observation, we propose feature Co-Action Network (CAN) to explore the potential of feature co-action. The proposed model can efficiently and effectively capture the feature co-action, which improves the model performance while reduce the storage and computation consumption. Experiment results on public and industrial datasets show that CAN outperforms state-of-the-art CTR models by a large margin. Up to now, CAN has been deployed in the Alibaba display advertisement system, obtaining averaging 12% improvement on CTR and 8% on RPM.


page 1

page 2

page 3

page 4


Feature Interaction based Neural Network for Click-Through Rate Prediction

Click-Through Rate (CTR) prediction is one of the most important and cha...

Feature Importance Measure for Non-linear Learning Algorithms

Complex problems may require sophisticated, non-linear learning methods ...

Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction

Click-through rate (CTR) prediction plays important role in personalized...

DynInt: Dynamic Interaction Modeling for Large-scale Click-Through Rate Prediction

Learning feature interactions is the key to success for the large-scale ...

Deep Collaborative Autoencoder for Recommender Systems: A Unified Framework for Explicit and Implicit Feedback

In recent years, deep neural networks have yielded state-of-the-art perf...

Optimizing Feature Set for Click-Through Rate Prediction

Click-through prediction (CTR) models transform features into latent vec...

An Empirical Experiment on Deep Learning Models for Predicting Traffic Data

To tackle ever-increasing city traffic congestion problems, researchers ...