Hi all
I have a 800 feature model that will like to compress by reducing the number of feautres and offcourse trying to maintain the accuracy levels as much as I can.
Is there an algorithm or a technique that I can implement over the features and found the ones that have the higest level of influence over the classes before training a model?
Have tough of training the model over 50 features each time and extract the best ones from every run but this process requiere a lot of computational resourse and was wondering if theres a better way?
Hello Alejandro,
You can try reducing the number of features by eliminating the highly correlated ones. Since correlated features might produce similar results for the prediction feature, you might get some benefit while getting rid of the correlated inputs.
Thanks