Optimizing derivative portfolios with fully general underlying and risk factor parameter uncertainty.

Derivatives are often treated as alien instruments by investment managers. However, once you separate exposures from market values, they become much easier to handle.

When it comes to portfolio optimization with parameter uncertainty, derivatives introduce an extra layer of complexity.

Since derivative P&L is a function of the underlying and other risk factors, such as implied volatility, we must introduce parameter uncertainty in a consistent way.

Luckily, our favorite views and stress-testing method, Entropy Pooling, provides an elegant solution to this problem.

Check out the updated article below, which includes accompanying Python code and even a video walkthrough: