chenfeng-huang/STDiffusion-ICDM-2025

Official implementation for STDiffusion, published in ICDM 2025.

37
/ 100
Emerging

This project helps researchers, analysts, and engineers generate realistic, diverse, and interpretable multivariate time series data. You provide existing time series datasets (like energy consumption, stock prices, or weather data), and it creates new synthetic time series samples. This is useful for tasks like data augmentation, privacy-preserving data sharing, or exploring 'what-if' scenarios.

Use this if you need to generate high-quality, synthetic time series data for analysis, forecasting, or imputation, especially when interpretability and realism are crucial.

Not ideal if you only need to perform basic forecasting or imputation on existing data without generating new synthetic samples.

time-series-analysis data-generation predictive-modeling financial-data environmental-modeling
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Jupyter Notebook

License

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/chenfeng-huang/STDiffusion-ICDM-2025"

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