kjpou1/regimetry
Unsupervised regime detection for financial time series using embeddings and clustering.
This tool helps financial traders and analysts identify recurring patterns in market behavior, known as 'regimes', without needing to pre-define them. You feed it historical financial time series data, and it outputs labels for different market states (like trends, reversals, or volatility shifts) along with visualizations to understand these transitions. It's designed for anyone looking to uncover hidden structures in market data for better strategy development.
No commits in the last 6 months.
Use this if you want an automated, data-driven way to discover and categorize distinct behavioral phases in financial markets from your historical time series data.
Not ideal if you need real-time, instantaneous regime detection for live trading, as there's a natural lag due to its windowed analysis approach.
Stars
11
Forks
5
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/kjpou1/regimetry"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TorchDR/TorchDR
TorchDR - PyTorch Dimensionality Reduction
derrickburns/generalized-kmeans-clustering
Production-ready K-Means clustering for Apache Spark with pluggable Bregman divergences (KL,...
abhilash1910/ClusterTransformer
Topic clustering library built on Transformer embeddings and cosine similarity...
md-experiments/picture_text
Interactive tree-maps with SBERT & Hierarchical Clustering (HAC)
mainlp/semantic_components
Finding semantic components in your neural representations.