Tredence Interview Questions | Distribution
Question
What could be some issues if the distribution of the test data is significantly different than the distribution of the training data?
in progress
0
Machine Learning
4 years
1 Answer
623 views
Great Grand Master 0
Answer ( 1 )
The model learns the pattern from the training data and then it tries to use the pattern to predict the test data. If the distribution of the test set is different than the training set, the pattern which the model, if applied to the test set will give poor results in terms of accuracy.