DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

TL;DR

DeepFM is an end-to-end neural network model that effectively captures both low- and high-order feature interactions for CTR prediction without requiring extensive feature engineering.

Contribution

It introduces a novel neural network architecture combining factorization machines and deep learning, eliminating the need for manual feature engineering.

Findings

DeepFM outperforms existing models on benchmark datasets.

It demonstrates high efficiency and effectiveness in CTR prediction.

The model works well on both benchmark and real-world commercial data.

Abstract

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.