Hybrid Wasserstein + HMM Regime Detection

This project reimagines the classical Merton portfolio optimization problem using Deep Reinforcement Learning (DRL). Instead of static, closed-form allocation rules, we design an intelligent agent that dynamically adjusts exposures to risky and risk-free assets under changing market regimes.

Machine learning project for predicting financial time-series returns using Random Forest with clustering-based market regime detection. Includes feature engineering with lag and rolling statistics, regime identification using K-Means and GMM, and PCA visualisation for analysing market states.

Mobile-first MRI-based market regime interpretation engine with risk-adjusted confidence modeling.

Machine learning approaches to market crash detection and early warning systems.

🚀 Optimize your portfolio with deep reinforcement learning, achieving superior returns and risk management in dynamic asset allocation.