ztxtech/cep_ts
This is an official PyTorch implementation of "Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting"
This project helps businesses and researchers make more accurate predictions when analyzing time-series data that changes its patterns over time, especially when old patterns reappear. You input your historical time-series data, and it outputs improved forecasts that adapt to these shifting trends without forgetting past knowledge. This is useful for data scientists, financial analysts, operations managers, or anyone relying on predictions from real-time data streams.
No commits in the last 6 months.
Use this if your online time-series forecasts are often inaccurate because the underlying data patterns (concepts) frequently change and reappear, leading to outdated models.
Not ideal if your time-series data has very stable patterns without significant, recurring concept shifts, or if you need to optimize for extremely low latency over prediction accuracy.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jun 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ztxtech/cep_ts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sktime/sktime
A unified framework for machine learning with time series
aeon-toolkit/aeon
A toolkit for time series machine learning and deep learning
Nixtla/neuralforecast
Scalable and user friendly neural :brain: forecasting algorithms.
tslearn-team/tslearn
The machine learning toolkit for time series analysis in Python
Nixtla/mlforecast
Scalable machine 🤖 learning for time series forecasting.