Recently I’ve been toying with the dark side.
Firstly I’ve been playing in Manufacturing. Despite living in a city that has been home to Jaguar, Rover and is just up the road from Aston Martin, I’ve never really been involved in that type of industry – until now.
Which leads to the second (and perhaps more relevant) part of this post. I’ve been looking into Root Cause Analysis. That’s the art of trying to find out why your auto has gone wrong. And it seems that there is a lot of scope for using predictive techniques within RCA, but with an interesting twist. I’m not using the algorithms to predict if your auto is going to fail, I’m using it simply to understand the important relationships that are associated with the failure.
So the question that I want to pose is this – is the CRISP-DM process model as relevant for this type of activity? Could modifications make it more relvant?
Isn’t that an instance of the concept description problem type. It definitely sounds like that to me, but perhaps I have missunderstood what CD is all about…
Comment by tuvelofstrom — February 27, 2007 @ 7:20 pm
CRISP can be thought of as a high level approach. That having been said, it would inded be possible to use CRISP as the framework within which to develop RCA projects. I would also say that there is definitely an application of Data Mining in RCA and using something like Apriori or Generalized Rule induction would begin to give you some understanding of relationships associated with failure.
Comment by walter2 — March 13, 2007 @ 3:45 am