chronos-forecasting
Prophet
chronos-forecasting | Prophet | |
---|---|---|
4 | 222 | |
1,901 | 17,893 | |
11.4% | 0.8% | |
7.7 | 7.0 | |
about 2 hours ago | 15 days 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
Prophet
- TimesFM (Time Series Foundation Model) for time-series forecasting
-
Moirai: A Time Series Foundation Model for Universal Forecasting
https://facebook.github.io/prophet/
"Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well."
- prophet: NEW Data - star count:17116.0
- prophet: NEW Data - star count:17082.0
- Facebook Prophet: library for generating forecasts from any time series data
- prophet: NEW Data - star count:16196.0
- prophet: NEW Data - star count:15889.0
What are some alternatives?
gluonts - Probabilistic time series modeling in Python
tensorflow - An Open Source Machine Learning Framework for Everyone
meta-prompting - Official implementation of BGPT @ ICLR 2024 paper "Meta Prompting for AI Systems" (https://arxiv.org/abs/2311.11482)
darts - A python library for user-friendly forecasting and anomaly detection on time series.
scikit-learn - scikit-learn: machine learning in Python
xgboost - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
greykite - A flexible, intuitive and fast forecasting library
MLflow - Open source platform for the machine learning lifecycle
Keras - Deep Learning for humans
sktime - A unified framework for machine learning with time series
pytorch-forecasting - Time series forecasting with PyTorch
Robyn - Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. Our mission is to democratise modeling knowledge, inspire the industry through innovation, reduce human bias in the modeling process & build a strong open source marketing science community.