decisionintelligence/DUET
[KDD 2025 Most Influential Paper] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
DUET helps you predict future trends in complex datasets that change over time, like stock prices or sensor readings from a factory. It takes historical multivariate time series data — multiple related data streams recorded over time — and generates accurate forecasts for what's likely to happen next. This is for data analysts, operations managers, or researchers who need to make informed decisions based on future predictions from real-world, interconnected time series.
259 stars.
Use this if you need highly accurate long-term forecasts for multiple, interdependent data streams, and you're dealing with diverse and sometimes erratic patterns.
Not ideal if you only need to forecast a single data stream or if your data patterns are very simple and don't require sophisticated modeling of interdependencies.
Stars
259
Forks
31
Language
Python
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/decisionintelligence/DUET"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.