Automatic Feature Engineering with Driverless AI

[@iyangarsamayal9517]

This is one of the finest videos on this topic I have seen anywhere. In fact, I bet more people would have seen it if it was correctly titled as “Secrets of building Great Machine Learning Models from a Kaggle Grand Master”. Seriously this video should be required viewing for all data scientists graduating from code academies, boot camps and masters degree programs since it is so important and so beautifully explained. Thank you Dmitry Larko!

[@hackstack4933]

It was a good session, thanks Dmitry!

[@NikTuzov]

Thanks for posting this, I learned a lot!

[@vidaringa1]

Shouldn't WtdEncode be the same value within each category, because the formula only uses the mean of the whole data set and the mean of the category? So for category A, WtdEncode should be 0.765, right?

[@victorpalacios1747]

Title is Automatic Feature Engineering. I wanted to learn how to do this in H20. This video does not cover this. The tutorials on the site should allow users to skip steps and get right to the topic they interested in, because we need to see how it all works before we use time trying to implement something we may not want.