ztxtech/Time-Evidence-Fusion-Network

Official implementation of "Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting" (https://arxiv.org/abs/2405.06419)

34
/ 100
Emerging

This project helps operations managers, financial analysts, and supply chain planners predict future trends from complex, long-term time series data. It takes in multiple streams of historical data and provides highly accurate, stable, and interpretable long-term forecasts. The Time Evidence Fusion Network (TEFN) is especially useful for decision-makers who need clear insights into how predictions are made, beyond just the numbers.

104 stars. No commits in the last 6 months.

Use this if you need to make critical decisions based on accurate, long-term predictions derived from multiple, sometimes uncertain, historical data sources and want to understand the reasoning behind the forecasts.

Not ideal if you only need short-term predictions or have very simple, single-source time series data that doesn't require advanced fusion techniques.

long-term forecasting multi-source data analysis predictive analytics demand planning operational planning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

104

Forks

4

Language

Python

License

MIT

Last pushed

Apr 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ztxtech/Time-Evidence-Fusion-Network"

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