XGBoost: prediction contributions

Published at March 10, 2019 ·  9 min read

In my most recent post I had a look at the XGBoost model object. I went through the calculations behind Quality and Cover with the purpose of gaining a better intuition for how the algorithm works, but also to set the stage for how prediction contributions are calculated. Since November 2018 this is implemented as a feature in the R interface. By setting predcontrib = TRUE the predict function returns a table containing each features contribution to the final prediction....

XGBoost: Quality & Cover

Published at March 7, 2019 ·  12 min read

I was going to write a post about how prediction contributions in XGBoost are calculated. But I quickly came to realize that it would be logical to go through a few other things first, namely Quality and Cover. Although this is all well described in the documentation, a practical example is sometimes useful. It has been very helpful for me at least in gaining a better understanding of how the algorithm works....