BTDLOZC-SJTU/TimeSeriesResearch
这个开源项目主要是对经典的时间序列预测算法论文进行复现，模型主要参考自GluonTS，框架主要参考自Informer
This project helps operations engineers, data scientists, and business analysts make more accurate forecasts for various real-world time series data, like electricity consumption, traffic, or financial exchange rates. It takes your historical time series data as input and provides not just single-point predictions but also probabilistic forecasts, helping you understand the uncertainty around future trends. This is useful for anyone who needs to predict future values with a better understanding of potential variations.
131 stars. No commits in the last 6 months.
Use this if you need to predict future values for complex time series data and want to understand the potential range of outcomes, rather than just a single number.
Not ideal if you prefer traditional, simple point forecasting models or are not working with time series data that requires understanding uncertainty.
Stars
131
Forks
8
Language
Python
License
—
Category
Last pushed
Jul 14, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BTDLOZC-SJTU/TimeSeriesResearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
sktime/sktime
A unified framework for machine learning with time series
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
tslearn-team/tslearn
The machine learning toolkit for time series analysis in Python
Nixtla/statsforecast
Lightning ⚡️ fast forecasting with statistical and econometric models.