Open-source investment analytics platform bridging academic research and retail finance. Features include portfolio risk decomposition [Fama-French Five Factor Model], retirement sustainability modeling [Block Bootstrap Monte Carlo], max drawdown/CVaR dashboards, and risk-return optimisation [Markowitz, Ledoit-Wolf] via an intuitive user interface.

This project focuses on building a portfolio optimization system using quantitative finance techniques.It implements Mean-Variance Optimization (Markowitz framework) to construct portfolios that maximize risk-adjusted returns.

Quantitative risk engine comparing robust Factor Models vs. NLP Semantic Hedging (LLMs) for tax-efficient portfolio management. Implements Huber regression, Nomic embeddings, and UMAP clustering.

🕹 Implement deep Q-network variants for Atari games with incremental improvements, enabling research and controlled experiments in deep reinforcement learning.