thuml/Nonstationary_Transformers

Code release for "Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting" (NeurIPS 2022), https://arxiv.org/abs/2205.14415

49
/ 100
Emerging

This project helps data scientists and machine learning engineers improve the accuracy of their time series predictions. It takes raw, real-world time series data, like electricity consumption or traffic flow, and produces more reliable forecasts than standard Transformer models. The primary users are researchers and practitioners working on advanced time series forecasting problems.

558 stars. No commits in the last 6 months.

Use this if you are a data scientist or researcher struggling with poor accuracy in long-term time series forecasting using existing Transformer-based models.

Not ideal if you need a simple, off-the-shelf solution for basic time series forecasting without deep engagement in model architecture.

time-series-forecasting predictive-modeling data-science machine-learning-research forecasting-accuracy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

558

Forks

102

Language

Python

License

MIT

Last pushed

Aug 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Nonstationary_Transformers"

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