I am looking for large datasets to investigate classification on time-dependent data where the data's features change over time.

An example of this might be a large spam dataset that covers a clear change in trends over time of constructing spam that can by-pass spam classifiers.

In other words are their any publicly available datasets available where it is clear that a classifier might have to be re-trained after a period of time to cope with feature changes?

  • What formats can you handle?
    – user4293
    Dec 6, 2016 at 16:23
  • The format doesn't really matter.
    – MattLBeck
    Dec 6, 2016 at 16:35


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Browse other questions tagged or ask your own question.