If the difference between the performance of your classifier on train and test sets is important , what may be happening?

Question

If the  difference  between the performance of your classifier on  train  and  test sets  is  important , what may be happening?

Answer

The  train  set is  not representative  of the  test  set.

Answer

The classifier may have  under-fitted .

Answer

The classifier is  not powerful enough  (capacity too low).

Answer

The classifier may have  over-fitted .

Answer

None of the options above.

Crowdly