Thinklab-SJTU/Crossformer

Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

48
/ 100
Emerging

This tool helps forecasters and analysts predict future values from complex, multi-faceted time-series data. You input historical records, like sensor readings from multiple locations or various financial indicators over time, and it outputs precise forecasts for upcoming periods. It is designed for anyone needing accurate predictions from numerous interconnected data streams.

669 stars. No commits in the last 6 months.

Use this if you need to accurately predict future trends for systems with many interacting variables, like energy consumption across different power plants or stock prices for an entire market sector.

Not ideal if your data is a simple, single time series, or if you require real-time, ultra-low-latency predictions on streaming data.

economic-forecasting energy-demand market-prediction sensor-monitoring operations-planning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

669

Forks

107

Language

Python

License

Apache-2.0

Last pushed

Dec 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Thinklab-SJTU/Crossformer"

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