Let's say you've trained a model for Hospital Readmission and want to get quick insights into what business rules D.Rs RuleFit models have come up with for this specific use-case.
Using an exceprt from Datarobot's Documentation on Insights, more specifically Hotspots,
"If the average readmission rate across your dataset is 40%, but for people with 10+ inpatient procedures it is 80%, then MRT is 2.00. That does not mean that people with 10+ inpatient procedures are twice as likely to be readmitted. Instead it tells you that this rule is twice better at capturing positive instances than just guessing at random using the overall sample mean."
I'm still confused as to what adopting this heuristic means for me? If I were to pitch this Heuristic to the concerned people in my organization, why would this be a Heuristic that they use? Why should they be convinced?
Unless these Heuristics are not actually meant to be used but to be interpreted and to extract insights from.
Am i supposed to look for Heuristics that incorporate a fair amount of rules, has a high M.R.T and has a high observation (%)?
On a final note, are Heuristics supposed to give you a rough idea on the outcome ? (in this case readmission) or is it supposed to give you somewhat conclusive evidence? Becuase there is no one Heuristic that covers the whole range of possible values unless you consider multiple Hueristics together. Am I right in thinking this?