Portfolio Construction and Optimization with Python

Pulls price data for assets (S&P 500 and gold), computes daily log returns with numpy, analyzes their correlation, and compares cumulative returns from 2010 onward.

Compare mean returns and volatility of gold versus the S&P 500 using Python tools. Gold shows a lower mean return but also lower standard deviation, indicating lower volatility.

Compute the portfolio's expected return by the dot product of a weights vector and asset returns, using numpy to create flexible equal weight vectors for any number of assets.

Learn how to compute portfolio risk by exact variance using a covariance matrix and weights, from simple two-asset cases to scalable matrix methods.

Compare the portfolio's risk and return with its single components to illustrate diversification. Show 50/50 gold and S&P 500 portfolio has risk lower than either asset and return between them.

Learn to compute the Sharpe ratio as risk-adjusted return, compare asset Sharpe ratios, and note a better return from an equally weighted S&P 500 and gold portfolio.

Add assets like Tesla to a portfolio, analyze correlations with gold and the S&P 500, and evaluate returns, risk, and Sharpe ratios to inform weight optimization for maximum risk-adjusted return.

Explore portfolio construction and optimization with Python by applying matrix algebra to optimize weights, using NumPy, Pandas, and SciPy minimize on assets like the S&P 500 and gold.

Learn to minimize the negative Sharpe ratio by computing portfolio risk from a covariance matrix and expected return from mean returns, using a weights vector for optimization.

Learn to optimize a portfolio by applying an equality constraint that forces weights to sum to one, enabling minimization of the Sharpe ratio via a solver.

Apply a Python optimization to minimize risk and maximize the Sharpe ratio, yielding optimal weights (33% and 67%) that overweight the S&P 500 and beat equal weights.

Learn to code a portfolio optimization from scratch by iterating over weight arrays, computing the Sharpe ratio, and identifying the weight split that minimizes the function.

Explore how train-test splits affect portfolio optimization, comparing train vs test performance and Sharpe ratios, using 70% train data to optimize and unseen test data to evaluate.

Add assets and apply short selling constraints by enforcing 0–1 bounds, compare equal versus optimized weights using train-test splits, and assess portfolio performance and Sharpe ratios.