Dear R Helpers,
At the moment I'm working on the project to implement "optimal binning"
function. It will be primarily used as a tool for logistic regression.....
something very similar to
http://www2.sas.com/proceedings/forum2008/153-2008.pdf* *but applied in
diferent problem space...*
*The problem might be descibed as finding optimal binning which will satisfy
all of the rules imposed:
- minimum and/or maximum percentage of observations per bin (good, bad, and
total)
- minimum and/or maximum bin width
- minimum and/or maximum number of bins
- minimum aggregate WOE difference between bins
- monotonicity of aggregate bin WOE values (increasing, decreasing, or a
combination)
- etc...
The idea is to use MILP (Mixed integer linear programming) and to solve
problem.....
Any ideas how to implement this would be welcomed...
even better... if someone is aware of any package which allready has this
functionaly... please us me know
Thanks for help.
--
This e-mail and any files transmitted with it are confid...{{dropped:14}}
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
