Training with very few positives
James Jong <ribonucleico <at> gmail.com> writes:
I have a binary classification problem where the fraction of positives is very low, e.g. 20 positives in 10,000 examples (0.2%) What is an appropriate cross validation scheme for training a classifier with very few positives?
[snip]
======================================== but I am not getting good performance (my ROC values are < 0.7 for all the classifiers above). Any thoughts?
My thought is that there probably just isn't any way to get good performance from this data set. The effective size of your data set is 20, which means it's very small, which means you may just have reached the limits of your predictive power ... Ben Bolker