0
$\begingroup$

I have n=1,000,000 data points with m=10 to m=60 attributes, i.e., m=10 to m=60 different variables. And I have a 1D output. I want to use support vector machine for classification. How would I do it so that it wouldn't take long for fitting the model. I am using Matlab.

Thanks

$\endgroup$

closed as unclear what you're asking by kjetil b halvorsen, John, mdewey, Michael Chernick, Firebug Jan 14 '17 at 17:05

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

1
$\begingroup$

LIBSVM is a great tool for performing SVM based classification (or regression).

https://www.csie.ntu.edu.tw/~cjlin/libsvm/

It supports MATLAB, so I think you'll find it useful.

But since LIBSVM doesn't scale up to a large dataset, it might take long depending on the dimensionality of your data and your environment. (although you can make it faster by turning on or off the shrinking heuristics option -h, theres no general rule for it)

In that case, I recommend you to refer to this post:

https://stackoverflow.com/questions/17457460/large-training-and-testing-data-in-libsvm

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.