decisionintelligence/DUET

[KDD 2025 Most Influential Paper] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting

52
/ 100
Established

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.

time-series-forecasting economic-modeling operations-analytics environmental-monitoring financial-prediction
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

259

Forks

31

Language

Python

License

MIT

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.