[1708.05123] Deep & Cross Network for Ad Click Predictions


DNNs are able to automatically learn feature interactions; however, they generate all the interactions implicitly, and are not necessarily efficient in learning all types of cross features. In this paper, the authors propose the Deep & Cross Network (DCN) which keeps the benefits of a DNN and introduces a novel cross network that is more efficient in learning certain bounded-degree feature interactions. 


Want to receive more content like this in your inbox?