0

In machine learning, an overfitted model fits training set very well but cannot generalize to new instances. I evaluated my model using cross-validation and my accuracy drops when setting the maximum number of splits of my decision tree beyond a certain number. Can this be associated with overfitting?

mc8
  • 315
  • 7
  • 21
  • The accuracy on your trainining or on your test set? – cangrejo Nov 26 '16 at 13:07
  • training set using cross-validation. This had me confused since I am using the same set of data but with cross-validation. – mc8 Nov 26 '16 at 13:21
  • I'm voting to close this question as off-topic because it belongs to http://datascience.stackexchange.com/ – Martin Thoma Nov 26 '16 at 13:25
  • then why are there tags related to this topic? @MartinThoma – mc8 Nov 26 '16 at 13:39
  • @mc8: StackOverflow is much better suited for implementation-related questions. For example, [How to use the a k-fold cross validation in scikit with naive bayes classifier and NLTK](http://stackoverflow.com/q/16379313/562769) is much more practical. Your question is independant of the implementation, thus it fits better to datascience.SE. Don't worry, you don't have to do anything. If 5 users decide that datascience.SE is a better fit for this question, it will be moved and you will get a notification. – Martin Thoma Nov 26 '16 at 14:31

0 Answers0