"High dimensional regression - the best (and fastest) approach with RM?"
brett_800
New Altair Community Member
I'm looking to model a regression target (ie: a continuous target). I have data sets that typically have more variables than observations.
What RM processes are best for feature selection/dimension reduction, and then modelling targets of this nature?
What RM processes are best for feature selection/dimension reduction, and then modelling targets of this nature?
Tagged:
0
Answers
-
You can attempt stochastic gradient descent based linear regression using the Optimization extension. You can use this for high dimensional and huge datasets
The extension is available at https://bitbucket.org/venkatesh20/optimization-extension
a video tutorial on this extension is available at https://www.youtube.com/watch?v=nECDYNT5owg0