Unsupervised regime detection for financial time series using embeddings and clustering.

Detecting market regimes using Hidden Markov Models on S&P 500 data

📈 Bitcoin trading system using Hidden Markov Models for market regime detection. Real-time signals, multi-timeframe analysis & interactive regime visualization.

Institutional-grade 5-phase quantitative analysis pipeline — 20+ indicators, HMM regime detection, GARCH volatility, walk-forward backtesting, Claude-powered trade notes.

Algorithmic trading engine for NSE. Regime-Adaptive Ensemble ML (XGBoost + LightGBM). Features automated bias auditing (CI/CD), Triple-Barrier Labeling, and dynamic risk management

Financial market regime detection using Hidden Markov Models for adaptive trading strategies

RBI-grade market regime detection & liquidity stress modelling using volatility, yield curves, and ensemble HMMs.

Macro regime research platform — 10-pillar scoring engine, live web dashboard, portfolio Greeks, Monte Carlo scenarios. CLI + Flask. Built for a PM morning risk meeting.

Financial Data Analytics Dashboard

A structured project for time series analysis and forecasting using statistical methods

LSTM-driven market regime detection with rule-based signal generation for systematic trading.

HMM-based market microstructure regime detection for cryptocurrency order books — 30+ features, Gaussian HMM, C++/pybind11 LOB engine, interactive Plotly Dash dashboard

Regime-based evaluation framework for financial NLP stability. Implements chronological cross-validation, semantic drift quantification via Jensen-Shannon divergence, and multi-faceted robustness profiling. Replicates Sun et al.'s (2025) methodology with modular, auditable Python codebase.

Deterministic rupture detection engine for financial time series using long-memory strain accumulation and state-machine confirmation.

📊 Detect market regimes by clustering probability distributions using Wasserstein K-means for more accurate financial analysis and insights.

Regime-aware quant risk and market stability monitoring framework.

Quantitative trading system for XAU/USD — PELT+BOCPD regime detection, RS-GBM Monte Carlo (N=10,000), ICT strategies. P(ruin)=0% across all stress tests.

This project applies unsupervised learning to detect latent financial market regimes from macro time series data. It emphasizes stability-based model selection across preprocessing, dimensionality reduction, and clustering methods.

Методология Геометрического Анализа Рынка. Классификация рыночных состояний через фазовое пространство.

Results-only repository publishing structural risk regime outputs from a private blackbox engine.