portfolio-optimization

To calculate the efficient frontier and maximum Sharpe portfolio, you solve convex optimization problems using estimated returns and covariance matrices with PyPortfolioOpt and cvxpy. This yields minimum-variance and tangency portfolios from your asset return series.

Black-Litterman portfolio optimization incorporates investor views by blending equilibrium or implied market returns with your subjective views to compute a statistically grounded posterior return estimate. This posterior is then used to solve for the optimized allocation.

Risk parity allocation is an approach where each asset contributes similarly to total portfolio volatility. It is computed by running covariance-driven convex optimization to solve for equal risk contribution weights across the selected assets.

Yes, you can backtest portfolio rebalancing strategies with walk-forward rolling windows. This performs periodic recalibration by re-estimating returns and covariance on rolling data to evaluate strategy performance under changing market scenarios.

Yes, you need cvxpy and PyPortfolioOpt for mean-variance optimization with constraints. These libraries provide the convex optimization solvers and financial structures required to compute efficient frontiers from estimated returns and covariance matrices.