Welcome back. I'm Lak, and I'm going to be talking about an extremely powerful feature engineering technique called Feature Crosses. In traditional machine learning, Feature Crosses don't play much of a role, but in modern day ML methods Feature Crosses are an invaluable part of your toolkit. In this model, you will learn how to recognize the kinds of problems where feature crosses are a powerful way to help machines learn. And once you learn how to recognize where to use the technique, the next step is to learn how to implement feature crosses in tenserflow. Now, your raw data will not contain Feature Crosses, you will have to create them from your raw inputs. So you will then learn how to incorporate feature creation as part of the machine learning pipeline. And finally, you will put all these lessons together to improve the taxifare model using Feature Crosses.