search

Nixtla / nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
https://docs.nixtla.io
Other
2.31k stars 187 forks source link

Covariates #413

Closed ozanbarism closed 3 months ago

ozanbarism commented 4 months ago

I saw this: Add Exogenous Variables: Incorporate additional variables that might influence your predictions to enhance forecast accuracy. (E.g. Special Dates, events or prices).

Does this mean we can use covariates? Example, I am trying to predict indoor air temperature. Can I also push outdoor air temperature to the model? If so, how can I do that?

marcopeix commented 4 months ago

Yes you can! Please, follow this tutorial on using exogenous variables.

elephaint commented 3 months ago

@ozanbarism Have you been able to solve your issue with the help of the tutorial? If not, let us know.

mergenthaler commented 3 months ago

Closing, but feel free to re-open if you have further questions.