For time series, we cannot just split the data and then shuffle it because the training and test sets would have high degree of correlation so we have to split it first and then shuffle each of the training and test separately but which way is recommended? Is it better to just split the whole dataset or split it in some intervals? For instance if we have 100 samples with a ratio of 70/30 should we put 1-70 in train or its better to put 1-7,11-17,21-27,....


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.