aliseyfi75/COSCI-GAN

Codebase for "Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)"

46
/ 100
Emerging

This project helps generate synthetic versions of complex, real-world multivariate time series data like stock prices or EEG readings. You input existing time series data, and it outputs new, artificial datasets that mimic the statistical properties and patterns of the original. This is useful for researchers and data scientists who need to expand datasets for training machine learning models or for privacy-preserving data sharing.

Use this if you need to create realistic, synthetic versions of multivariate time series data where channels are related, such as financial trading data, sensor readings, or biological signals.

Not ideal if you are looking to generate simple, independent time series or if your primary need is for anomaly detection rather than data generation.

time-series-generation data-synthesis financial-modeling biosignal-analysis machine-learning-data-prep
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

36

Forks

9

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aliseyfi75/COSCI-GAN"

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