The 'shuttle' data can be downloaded from the link here.

It is imbalanced data and there are two classes in the target variable. The proportion of the two classes are seven percent. I used Logistic Regression and Autoencoders to classify them; but, Logistic Regression performed better than Autoencoders.


LR is 0.953
AE is 0.946



LR is 0.999
AE is 0.939

Is this a reasonable result? Thanks.

  • $\begingroup$ An autoencoder is a method for data compression, not for prediction. Thus, the question does not seem to make sense. $\endgroup$ – Michael M May 6 '19 at 2:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.