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.
Recall: LR is 0.953 AE is 0.946
Precision: LR is 0.999 AE is 0.939
Is this a reasonable result? Thanks.