% Constructing Portfolios of Dynamic Strategies using Downside Risk Measures % Peter Carl, Hedge Fund Strategies, William Blair & Co. % November 11, 2013
# R code here
...broadly described as periodically reallocating the portfolio to achieve a long-term goal
Here we'll consider a strategic allocation to hedge funds
Monthly data of EDHEC hedge fund indexes from 1998
\includegraphics[width=1.0\textwidth]{../results/EDHEC-Cumulative-Returns.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-RollPerf.png}
Add table of relevant statistics here
system('cat results/EDHEC-inception-cor.md')
\includegraphics[width=0.5\textwidth]{../results/EDHEC-cor-inception.png} \includegraphics[width=0.5\textwidth]{../results/EDHEC-cor-tr36m.png}
In constructing a portfolio, most investors would prefer:
Construct a portfolio that:
\includegraphics[width=1.0\textwidth]{../results/EDHEC-Distributions.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-Distributions2.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-ACStats.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-ACStackedBars.png}
Measure risk with Conditional Value-at-Risk (CVaR)
\includegraphics[width=1.0\textwidth]{../results/EDHEC-BarVaR.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-BarVaR2.png}
\includegraphics[width=1.0\textwidth]{../results/EDHEC-ETL-sensitivity.png}
Ex post analysis of risk contribution has been around for a while
The use of ex ante risk budgets is more recent
We want to look at the allocation of risk through ex ante downside risk contribution
Use the modified CVaR contribution estimator from Boudt, et al (2008)
We can use CVaR contributions as an objective or constraint in portfolio optimization
Constraints specified for each asset in the portfolio:
Table of Return, Volatility, Skew, Kurt, and Correlations by asset
Equal contribution to:
Reward to risk:
Minimum:
insert table
The risk parity constraint that requires all assets to contribute to risk equally is usually too restrictive.
Risk Budget as an eighth objective set
From a portfolio seed, generate random permutations of weights that meet your constraints
Sampling can help provide insight into the goals and constraints of the optimization
\includegraphics[width=1.0\textwidth]{../results/RP-EqWgt-MeanSD-ExAnte.png}
\includegraphics[width=1.0\textwidth]{../results/RP-Assets-MeanSD-ExAnte.png}
\includegraphics[width=1.0\textwidth]{../results/RP-BUOY-MeanSD-ExAnte.png}
\includegraphics[width=1.0\textwidth]{../results/RP-BUOYS-mETL-ExAnte.png}
\includegraphics[width=1.0\textwidth]{../results/Weights-Buoys.png}
\includegraphics[width=1.0\textwidth]{../results/mETL-CumulPerc-Contrib-Buoys.png}
As a framework for strategic allocation:
Figure out bibtex links in markup
http://www.portfolioprobe.com/about/random-portfolios-in-finance/
Slides after this point are not likely to be included in the final presentation
All numerical optimizations are a tradeoff between speed and accuracy
Differential evolution will get more directed with each generation, rather than the uniform search of random portfolios
Allows more logical 'space' to be searched with the same number of trial portfolios for more complex objectives
doesn't test many portfolios on the interior of the portfolio space
Early generations search a wider space; later generations increasingly focus on the space that is near-optimal
Random jumps are performed in every generation to avoid local minima
Insert Chart
GenSA, SOMA,
scatter plot with both overlaid
scatter chart colored by degree of turnover
scatter chart of RP colored by degree of concentration (HHI)
Slides likely to be deleted after this point
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.