Summary: Deep & Cross Net v2 (opens in new tab)

Paper link: Learning to rank is an important problem in many machine-learning products such as search, recommendation, and advertising. Originally, many machine learning systems used simple logistic regression models, but it quickly became apparent that combining two or more features together was even better. This is called feature crossing. A lot of research and engineering work has gone into learning useful feature crosses. The fundamental problem is that although higher-order feature cross...