Meucci GSOC 2013
Extend the functionality of the
Meucci package with additional research by Attilio Meucci, a thought leader in risk and portfolio management.
Attilio Meucci is a pioneer in advanced risk and portfolio management. His innovations include Entropy Pooling (technique for fully flexible portfolio construction), Factors on Demand (on-the-fly factor model for optimal hedging), Effective Number of Bets (entropy-eigenvalue statistic for diversification management), Fully Flexible Probabilities (technique for on-the-fly stress-test and estimation without re-pricing), and Copula-Marginal Algorithm (algorithm to generate panic copulas). Attilio Meucci serves as the chief risk officer at Kepos Capital LP. Concurrently, he is adjunct professor at the Master’s in Financial Engineering – Baruch College - CUNY.
Prof. Meucci frequently includes Matlab code alongside his key papers to better demonstrate the concepts. We have started and would like to continue to convert that code to R to make it more widely assessible.
During last summer’s GSoC, we sponsored a related project that benefited from a very generous contribution of ported code from Ram Ahluwalia at Wingfoot Capital. The project focused on that code contribution and established a stand-alone package named
Meucci that is now available on r-forge at https://r-forge.r-project.org/scm/viewvc.php/pkg/Meucci/?root=returnanalytics. That package now contains twenty-some exported functions and six demos, along with some degree of documentation for most of them. There is still much to do here, but the package will provide a good foundation for the proposed work.
All of Meucci’s original MATLAB source is available on www.symmys.com, where you can examine the extensive material he makes available.
Beyond the initial conversion of functions from the MATLAB code, we will functionalize certain functions to include in PerformanceAnalytics, PortfolioAnalytics, or developing a package around one or more of the concepts described above, starting with the Effective Number of Bets. PerformanceAnalytics is an R package that provides a collection of econometric functions for performance and risk analysis. PortfolioAnalytics is an extensible business-focused framework for portfolio optimization and analysis.
This project will be pursued in three pieces. In the first, the student will focus on Meucci (2012), where he provides a framework for computing, stress-testing, and managing liquidity risk, funding risk and market risk in fully general multi-asset class portfolio. Specifically, this will include porting Meucci’s MATLAB code and carefully verifying the resulting calculations to ensure that results match, from the following papers:
In the second part of the project, the student will functionalize certain workflows to include in PerformanceAnalytics or other appropriate packages. This portion of the project may focus on either the liquidity concept described above, or Meucci’s Effective Number of Bets concept, described in Meucci (2010).
The third part of the project will focus on the continued improvement of the Meucci package. This will include refining functionality to remove the need for the matlab package, identifying and reducing functional overlap, adding more charts and graphs, and improving the documentation and examples.
Applicants should have:
A successful applicant will:
David Ardia is a co-author with Attilio Meucci, author of the DEoptim package, and has previously mentored GSoC projects.
Brian Peterson is one of the primary authors of the related packages, and has previously mentored GSoC projects including the Meucci project from GSoC 2012.
Peter Carl is one of the primary authors of the related packages and has previously mentored GSoC projects.