Interpretability: Cracking open the black box – Part II

In the last post in the series, we defined what interpretability is and looked at a few interpretable models and the quirks and'gotchas' in it. Now let's dig deeper into the post-hoc interpretation techniques which is useful when you model itself is not transparent. This resonates with most real world use cases, because whether we like it or not, we get better performance with a black box model. For this exercise, I have chosen the Adult dataset a.k.a Census Income dataset. Census Income is a pretty popular dataset which has demographic information like age, occupation, along with a column which tells us if the income of the particular person 50k or not. We are using this column to run a binary classification using Random Forest.