Filter-based Portfolio Strategies in an HMM Setting with Varying Correlation Parametrizations

31 Pages Posted: 2 Dec 2016 Last revised: 24 Nov 2017

See all articles by Christina Erlwein-Sayer

Christina Erlwein-Sayer

Fraunhofer Gesellschaft - Institute of Industrial Mathematics (ITWM)

Stefanie Grimm

Fraunhofer Gesellschaft - Department of Finance

Peter Ruckdeschel

University of Oldenburg - School of Mathematics and Science

Jörn Sass

University of Kaiserslautern - Department of Mathematics

Tilman Sayer

Advanced Logic Analytics

Date Written: November 28, 2016

Abstract

We consider portfolio optimization in a regime-switching market. The assets of the portfolio are modeled through a hidden Markov model (HMM) in discrete time, where drift and volatility of the single assets are allowed to switch between different states. We consider different parametrizations of the involved asset covariances namely state-wise uncorrelated assets, which are though linked through the common Markov chain, assets correlated in a state-independent way, and assets where the correlation varies from state to state. As a benchmark we also consider a model without regime switches. We utilize a filter-based EM-algorithm to obtain optimal parameter estimates within this multivariate HMM and present parameter estimators in all three HMM settings. We discuss the impact of these different models on the performance of several portfolio strategies. Our findings show that for simulated returns our strategies often outperform naive investment strategies, like the equal weights strategy. Information criteria can be used to detect the best model for estimation as well as for portfolio optimization. A second study using real data confirms these findings.

Keywords: Multivariate HMM, Filtering, Regime switching model, Portfolio optimization

Suggested Citation

Erlwein-Sayer, Christina and Grimm, Stefanie and Ruckdeschel, Peter and Sass, Jörn and Sayer, Tilman, Filter-based Portfolio Strategies in an HMM Setting with Varying Correlation Parametrizations (November 28, 2016). Available at SSRN: https://ssrn.com/abstract=2876807 or http://dx.doi.org/10.2139/ssrn.2876807

Christina Erlwein-Sayer (Contact Author)

Fraunhofer Gesellschaft - Institute of Industrial Mathematics (ITWM) ( email )

Gottlieb-Daimler-Str., Geb. 49
67663 Kaiserslautern, 67663
Germany

Stefanie Grimm

Fraunhofer Gesellschaft - Department of Finance ( email )

Gottlieb-Daimler-Str., Geb. 49
67663 Kaiserslautern
Germany

Peter Ruckdeschel

University of Oldenburg - School of Mathematics and Science ( email )

PO box 2503
Oldenburg, 26111
Germany

Jörn Sass

University of Kaiserslautern - Department of Mathematics ( email )

D-67653 Kaiserslautern
Germany

Tilman Sayer

Advanced Logic Analytics

London
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
140
Abstract Views
854
rank
223,664
PlumX Metrics