chronos-forecasting
mvts_transformer
chronos-forecasting | mvts_transformer | |
---|---|---|
4 | 1 | |
1,810 | 697 | |
28.3% | - | |
6.8 | 0.0 | |
4 days ago | 9 months ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
chronos-forecasting
-
TimesFM (Time Series Foundation Model) for time-series forecasting
On a related note, Amazon also had a model for time series forecasting called Chronos.
https://github.com/amazon-science/chronos-forecasting
-
Financial Market Applications of LLMs
There were some developments using LLMs in the timeseries domain which caught my attention.
I toyed with the Chronos forecasting toolkit [1], and the results were predictably off by wild margins [2]
What really caught my eye though was the "feel" of the predicted timeseries -- this is the first time I've seen synthetic timeseries that look like the real thing. Stock charts have a certain quality to them, once you've been looking at them long enough, you can tell more often than not whether some unlabeled data is a stock price timeseries or not. It seems the chronos LLM was able to pick up on that "nature" of the price movement, and replicate it in its forecasts. Impressive!
1: https://github.com/amazon-science/chronos-forecasting
2: https://imgur.com/a/hTRQ38d
-
Chronos: Learning the Language of Time Series
https://github.com/amazon-science/chronos-forecasting
- Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
mvts_transformer
-
Chronos: Learning the Language of Time Series
Like this or something different?
https://github.com/gzerveas/mvts_transformer
What are some alternatives?
gluonts - Probabilistic time series modeling in Python
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 🚀.
meta-prompting - Official implementation of BGPT @ ICLR 2024 paper "Meta Prompting for AI Systems" (https://arxiv.org/abs/2311.11482)