[R] Recursive partitioning algorithms in R vs. alia

[Peter Flom]

"Carlos J. Gil Bellosta" <cgb at datanalytics.com> wrote
>
>I had a conversation with a guy working in a "business intelligence"
>department at a major Spanish bank. They rely on recursive partitioning
>methods to rank customers according to certain criteria. 
>
>They use both SAS EM and Salford Systems' CART. I have used package R
>part in the past, but I could not provide any kind of feature comparison
>or the like as I have no access to any installation of the first two
>proprietary products.
>
>Has anybody experience with them? Is there any public benchmark
>available? Is there any very good --although solely technical-- reason
>to pay hefty software licences? How would the algorithms implemented in
>rpart compare to those in SAS and/or CART?
>
>Best regards,
>

Hi

I've used CART and a few different R packages - tree, rpart, rparty.

I can't comment on the algorithms - I'm not qualified to judge, and I think
the ones in CART are proprietary.

One big difference is that the output from CART is beautiful with
minimal fuss.  Presentation quality, multicolor, multipage tree diagrams
with the default settings.

Another was speed - I am not sure I was doing everything right in R, but
for one problem I had that had about 500 variables, R was quite slow, and CART
blitzed through it.

Another big difference is the price.  I got CART for a reasonable fee, as 
I was working at a university, but the commercial price is very high (well into
the thousands of dollars, if I recall correctly).

Peter


Peter L. Flom, PhD
Statistical Consultant
www DOT peterflomconsulting DOT com