Assume that I have a data set generated from two separate classes and my data set includes a good balanced set of each classes.

I have used Logistic Regression and Support Vector Machine to train a classifier on this data set and I cannot get an F1 Measure better than 0.6. I have tried different regularization parameters and have done cross-validation.

What does this mean? What should I do to train a classifier?

A. Reduce the amount of data from one of the classes.

B. Include more data from one of the classes in the training set.

C. If you have check all of the model parameters and tested different data sets. This might be a sign that the data is not linearly separable, you should use other classification models like kNN or RandomForest.

D. Get more data. Having larger sample data always help to improve the performance.

E. None of the above.