Portfolio Optimization with PyPortfolioOpt

What problem does it solve?

This Skill provides a Python-based workflow for portfolio optimization using PyPortfolioOpt, covering expected returns calculation, risk models, and multiple optimization strategies (Efficient Frontier, Black-Litterman, HRP).

Core Features & Use Cases

• Expected Returns: compute annualized returns from price data
• Risk Models: estimate covariance with several approaches (sample_cov, Ledoit-Wolf, denoised_covariance, etc.)
• Optimization Techniques: max Sharpe, min volatility, max utility, HRP, Black-Litterman
• Use Case: allocate across assets to balance return and risk under real-world constraints

Quick Start

Prepare a prices DataFrame, compute mu and S, choose an optimization, run it, and retrieve weights and performance metrics.