Hi, In the GeneralizedLinearAlgorithm, which Logistic Regression relied on, it says "if userFeatureScaling is enabled, we will standardize the training features ...., and trained the model in the scaled space. Then we transform the coefficients from the scaled space to the original space ...".
My understanding then is we do not need to scale the test data since the coefficients are already in the original space, is this correct? Thanks Jianguo