DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
This addresses the need for improved CTR prediction in recommender systems without requiring feature engineering, though it is incremental as it builds on prior models like factorization machines and Wide & Deep.
The paper tackles the problem of learning both low- and high-order feature interactions for CTR prediction in recommender systems, proposing DeepFM, which combines factorization machines and deep learning in a neural network architecture, and shows effectiveness over existing models like Wide & Deep in experiments on benchmark and commercial data.
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise feature engineering. In this paper, we show that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions. The proposed model, DeepFM, combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture. Compared to the latest Wide \& Deep model from Google, DeepFM has a shared input to its "wide" and "deep" parts, with no need of feature engineering besides raw features. Comprehensive experiments are conducted to demonstrate the effectiveness and efficiency of DeepFM over the existing models for CTR prediction, on both benchmark data and commercial data.