For a problem where we need to optimize the portfolio based on the data, going for Markowitz MPT has the following advantage: we only have to estimate mean and covariance to find optimal weights. I'd call this approach model-free as it does not require constructing a model for the evolution of the constituents of the portfolio. I wonder if comparable techniques are available for dynamic portofilo rebalancing. There is a multitude of methods in case you've got a model: for example, you can apply stochastic optimal control via dynamic programming, however I am interested in model-free methods.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.