I implemented and deployed with Flask an XGBoost model for a classification problem. But being aware that features importance can change over time to predict probability of label for new data, I implemented a Cron so that the model can be retrained every two weeks.

But I don't know how I can handle new features since I would have to wait a great volume of data to retrain the model to take into account this new feature ?

Is there an alternative of model deployment to this problem ?

| improve this question | | | | |

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.