Categorical Root Cause Analysis

Hi everyone,

We're trying to solve a problem that I feel should be rather generic, and for some reason I can't seem to find good material about.

So the problem goes like this: we have a certain metric that we want to maximize, within a range of 0-100%. This metric is computed as the percentage of 1s in a binary column in our dataset. All of the other columns are categorical features, with varying cardinalities. Some might have 3 possible …

analysis categorical datascience good material reason root cause analysis solve