Can we use XGboost to do predition in time series data ? Could anyone explain the logic of mathematics behind that ?

  • 3
    $\begingroup$ Yes you can but traditional time-series tools (ARIMA, ETS etc.) would probably give you better results. $\endgroup$ – Tim Nov 16 '17 at 16:15

Yes, I recommend reviewing this package, its documentation and citations:


Keep in mind, XGB does not typically outperform current time-series methods such as exponential smoothing or ARIMA.

| cite | improve this answer | |

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.