run your code on my data on specific variable (Nr Years in bank )
In your code the best group should be 1 and worse should be 4
I don't see that Per increasing consistently by moving from group 1 to 2 and 2 to 3 and 3 to 4.
Is it not part of the requirement??? To have consistently increasing in per (percentage of bads)???
The code you send me is running 100%
It provide good results but my friend provide better results via Miner (IGN)
It would be best if can provide such results in SAS code.
By the way- what is the alogorithm name that you used in your code?
"It provide good results but my friend provide better results via Miner (IGN)"
You could try SAS/EM 's ScoreCard module,but that need money to pay.
And I never heard of Miner ,what kind of software it is?
"It would be best if can provide such results in SAS code."
1)You could ask @RobPratt to write SAS/OR code for it ,and also need to pay money to get SAS/OR.
2)Make %let n_iter=10000 ; as big as you can , but that maybe cost you an entire day to get better result.
And make the following 1000 as big as you can. E.X. 10000
call gainit(id,1000,encoding);
--->
call gainit(id,10000,encoding);
"what is the alogorithm name that you used in your code?"
Genetic Algorithm. Check @Rick_SAS blog:
https://blogs.sas.com/content/iml/2021/10/20/intro-genetic-algorithms-sas.html
https://blogs.sas.com/content/iml/2021/10/18/crossover-mutation.html
You might be interested in PROC OPTBINNING:
Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.
Register today!Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Select SAS Training centers are offering in-person courses. View upcoming courses for: