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

feat: distinguish between historical and future exogenous variables in cross validation #522

Open AzulGarza opened 1 week ago

AzulGarza commented 1 week ago

Description

currently, cross-validation is designed to treat all exogenous variables as future variables by default. moving forward, we aim to align cross-validation settings more closely with forecast settings, enabling differentiation between historical and future exogenous variables.

Use case

No response