Journal of Investment Strategies

Risk.net

Extending risk budgeting for market regimes and quantile factor models

Emlyn Flint and Simon du Plooy

  • We extend an existing risk-based optimisation framework to allow market regimes and non-linear factor dependencies.
  • This framework is only comprised of a series of linear models, and is thus tractable and simple to implement.
  • We consider two applications of the extended framework, namely scenario analysis and parameter uncertainty analysis.
  • We also introduce the concept of Risk Maps, which provide managers with a graphical approach for estimating and evaluating risk optimality in a multi-objective and multi-scenario setting.

We combine several disparate avenues in the literature to create a novel, unified risk- based optimization framework. Specifically, we extend an existing risk-budgeting approach to allow for changing market regimes and factor dependence as well as a nonlinear, asymmetric market structure. We show that the existing framework can be readily extended to include a factor-dependent return process using standard models available in the literature. Structural changes in the market conditions are then incorporated into the framework via the use of a regime-switching turbulence index, and the nonlinear and asymmetric market dependence structure is accounted for by using quantile factor models. Most importantly, this extended framework is comprised of a series of linear models only and is thus simple to understand and to implement. We consider two applications of the extended framework, namely, scenario analysis and parameter uncertainty analysis, by way of a simple empirical case study. Finally, we introduce the concept of risk maps, which provide managers with a graphical approach for estimating and evaluating risk optimality in a multiobjective, multiscenario setting.

To continue reading...

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an indvidual account here: