[DOCS] add tutorial on how tu use TimeGPT for long-horizon tasks

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

1.91k stars 151 forks source link

[DOCS] add tutorial on how tu use TimeGPT for long-horizon tasks #245

Closed AzulGarza closed 3 months ago

AzulGarza commented 4 months ago

the main idea is to create a tutorial based on this section of the faqs. currently, the example there uses AirPassengers, but it would be great to use a high-frequency dataset (for instance, Hourly or SubHourly), since the long-horizon tasks are specialized in this kind of data.

AzulGarza commented 4 months ago

hey @marcopeix! i tagged you in this issue ;)

marcopeix commented 3 months ago

PR merged, tutorial is now available. Closing.