After reading 'Advances in Financial Machine Learning' by Marcos Lopez de Prado, I wonder how can we train machine learning algorithm with too few financial data. If we use cumsum filter etc the number of data available for training decreases dramatically. Though the number of data decreases, is it still okay because we have the best quality financial data?

Quality of data <-> Number of data, which one is more desirable?


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.