I run different classification algorithms on my data on got AUC value less than 50%. For algorithm A I obtained around 60%, but algorithm B, C and D close to 50% such as 46%, 47% and 42%. So my question is what are the main reasons to have such AUC values that I can discuss in my report?my other question is; Can I consider the 50% as the baseline to assess the classifier performance, or I need to calculate the base-line for each classifier separately and then assess them. If yes How can I calculate a base-line for AUC.

closed as too broad by Sycorax, Peter Flom Aug 12 at 10:51

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 3
    It is hard to comment without further details. Maybe your data is just rubbish? – Tim Aug 10 at 10:10
  • 1
    It could be because of feature engineering as well. – Upasana Mittal Aug 10 at 20:03
  • Maybe your data are fine but your model is no good. That is, the predictors don't predict. – Peter Flom Aug 12 at 10:51
  • Yes, somehow the data is a bit strange, but I read from different sources, mostly this is because of the classifier which do not work properly on this data. – nahid khosh Aug 12 at 14:20