Multi-Period Portfolio Selection with Drawdown Control
Lists
Only you see this
Abstract
In this talk, model predictive control (MPC) is used to dynamically optimize an investment portfolio. Thepredictive control is based on multi-period forecasts of the mean and covariance of financial returns from amultivariate hidden Markov model with time-varying parameters. Estimation and forecasting are done using anonline expectation--maximization algorithm. There are computational advantages to using MPC when estimatesof future returns are updated every time new observations become available, since the optimal control actions arereconsidered anyway. Transaction and holding costs are important and are discussed as a means to addressestimation error and regularize the optimization problem. A complete practical implementation is presentedbased on available market indices chosen to mimic the major liquid asset classes typically considered by aninstitutional investor. In an out-of-sample test spanning two decades, the proposed approach to multi-periodportfolio selection successfully controls drawdowns with little or no sacrifice of mean--variance efficiency.
BibTeX
@article{nystrup2019multi,
author = {Peter Nystrup and Henrik Madsen and Stephen Boyd and Erik Lindström},
title = {{Multi-Period Portfolio Selection with Drawdown Control}},
journal = {Ann. Oper. Res.},
year = {2019},
doi = {10.1007/s10479-018-2947-3},
}Loading related content...