The recommendation systems task is to produce a list of recommendations for a user.
User response prediction is a crucial component for personalized information retrieval and filtering scenarios, such as recommender system and web search.
In this paper, we study two instances of DeepFM where its "deep" component is DNN and PNN respectively, for which we denote as DeepFM-D and DeepFM-P. Comprehensive experiments are conducted to demonstrate the effectiveness of DeepFM-D and DeepFM-P over the existing models for CTR prediction, on both benchmark data and commercial data.
On one hand, the xDeepFM is able to learn certain bounded-degree feature interactions explicitly; on the other hand, it can learn arbitrary low- and high-order feature interactions implicitly.
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems.
Predicting user responses, such as clicks and conversions, is of great importance and has found its usage in many Web applications including recommender systems, web search and online advertising.
Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort.
#2 best model for Click-Through Rate Prediction on Bing News