machine learning using base SAS

[eagles_dare13]

Is there a way to access machine learning algorithms like random forests, support vector machines using bases sas and enterprise guide only? Or do we need to have SAS enterprise miner installed?

[Reeza]

You need Enterprise Miner

[art297]

Or look into R. With either IML or WPS you can run R on SAS data quite easily.

[PatrickHall · Accepted solution]

Ok sure ... you will need EM for random forests and support vector machines.

And I do like to use ML packages from R on SAS data, especially gbm and randomForest. You will have to have IML (or EM) licensed to do this. Do you have IML licensed? If you do, I will post some example code.

BUT I have to say that SAS/STAT - which nearly everyone who installs SAS should have - has been a leader in the fields of Machine Learning and Statistical Learning since the early 1980s. There is enough ML in SAS/STAT to serve many different needs, including the types of difficult classification and regression problems for which random forest and SVM are often used.

I often advise users to try more standard regression models before moving onto machine learning algorithms anyway. Sometimes the regression models, or discriminant analysis models, will out-perform machine learning methods that are also basically uninterpretable. You should only sacrifice the interpretability of more traditional models if you get better results from a ML technique or your data requires that you use a non-traditional approach.

By my count these are the machine learning procedures in SAS/STAT 13.2:

ACECLUS

ADAPTIVEREG

CLUSTER

DISCRIM

DISTANCE

FACTOR

FASTCLUS

GLIMMIX

KDE

KRIGE2D

LOGISTIC

MCMC

MDS

MODECLUS

NLIN

PLS

PRINCOMP

REG

ROBUSTREG

VARCLUS

[Reeza]

You make a very good point

[TimBrowning]

Great list. I would also include GLMSELECT in the list (stepwise) for ML type applications where you don't know what are the best features to use in a predictive model. For example, a system state may be described by hundreds of features and you want to predict the future state of one of those features given the past state of the total system. GLMSELECT can help you select the best features to use for a regression model. In addition, you can use training, test and validation samples to minimize overfitting.

[prasad_clinical]

You can use Proc SVM to perform Support vector Machine(Maximum Margin Classifier). and TRy with Randomwoods statement for Random Forest.