gregorLen/S-ANFIS-PyTorch

An Implementation of the State-Adaptive Neuro-Fuzzy Inference System (S-ANFIS) based on Pytorch. Also Repository to my package "sanfis".

39
/ 100
Emerging

This project helps quantitative analysts and researchers to model complex, regime-switching time series, especially in financial contexts. It takes historical time-series data, split into 'state' variables that define the regime and 'input' variables that explain the outcome within a regime. The output is a predictive model that adapts to different underlying states, providing more accurate forecasts for dependent variables like asset prices or economic indicators.

No commits in the last 6 months.

Use this if you need to build flexible, interpretable models for time series data where the relationships between variables change depending on observable 'state' conditions or regimes.

Not ideal if your time series data exhibits strictly linear relationships or if you prefer black-box models that prioritize predictive power over interpretability.

quantitative-finance economic-forecasting time-series-analysis financial-modeling regime-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

30

Forks

6

Language

Python

License

MIT

Last pushed

Aug 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gregorLen/S-ANFIS-PyTorch"

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