Levi-Ackman/Leddam

[ICML 2024] Official implementation of: "Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling".

27
/ 100
Experimental

This project helps data scientists, analysts, and researchers forecast future values in complex datasets where multiple related measurements change over time. It takes in historical multivariate time series data and produces accurate predictions for what those series will look like in the future. This is ideal for anyone needing to make robust predictions across interconnected time-dependent variables.

No commits in the last 6 months.

Use this if you need to make highly accurate predictions on datasets with many interdependent time-series, such as forecasting energy consumption across different grid points or predicting stock prices for an entire portfolio.

Not ideal if you are working with simple, single time-series forecasting problems or require real-time, ultra-low-latency predictions on streaming data.

multivariate-forecasting time-series-analysis predictive-modeling data-analytics operations-planning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

79

Forks

7

Language

Python

License

Last pushed

Feb 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Levi-Ackman/Leddam"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.