Nixtla/nixtla

TimeGPT-2.1: 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 🚀.

52 best points · 16 comments · 5 Hacker News posts · 4,042 GitHub stars · View on GitHub

Hacker News discussions

• TimeGPT: Production Ready Time Series Foundation Model for Forecasting (52 points, 7 comments, by LevoMX, 2024-05-08)
• Automated Time Series Processing and Forecasting (38 points, 8 comments, by fedegr, 2021-12-05)
• Benchmarking foundation models for time series (4 points, 0 comments, by LevoMX, 2024-05-29)
• Is linear regression better than prophet? Zillow benchmark (2 points, 1 comments, by fedegr, 2022-01-07)
• Prophet vs. Linear Regression on Real Estate: The Zillow Case (1 points, 0 comments, by fedegr, 2021-12-13)