论文信息 - Differential Evolution (DEoptim) for Non-Convex Portfolio Optimization

Differential Evolution (DEoptim) for Non-Convex Portfolio Optimization

The R package DEoptim implements the differential evolution algorithm. This algorithm is an evolutionary technique similar to genetic algorithms that is useful for the solution of global optimization problems. In this note we provide an introduction to the package and demonstrate its utility for financial applications by solving a non-convex portfolio optimization problem.

[1] O. Scaillet. Nonparametric Estimation and Sensitivity Analysis of Expected Shortfall , 2004 .

[2] Dietmar Maringer,et al. Smooth Transition Autoregressive Models – New Approaches to the Model Selection Problem , 2006 .

[3] David Ardia,et al. DEoptim: An R Package for Global Optimization by Differential Evolution , 2009 .

[4] Sandra Paterlini,et al. Multiobjective optimization using differential evolution for real-world portfolio optimization , 2011, Comput. Manag. Sci..

[5] Dietmar Maringer,et al. Index tracking with constrained portfolios , 2007, Intell. Syst. Account. Finance Manag..

[6] Dietmar Maringer,et al. Portfolio management with heuristic optimization , 2005 .

[7] Sandra Paterlini,et al. Differential evolution and combinatorial search for constrained index-tracking , 2009, Ann. Oper. Res..

[8] R. Storn,et al. Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[9] Manfred Gilli,et al. Heuristic optimisation in financial modelling , 2010, Annals of Operations Research.

[10] Peter Winker,et al. A Review of Heuristic Optimization Methods in Econometrics , 2008 .

[11] Peter Winker,et al. Applications of Heuristics in Finance , 2008 .

[12] Steven I. Higgins,et al. Sustainable management of extensively managed savanna rangelands , 2007 .

[13] Ricardo Cao,et al. Modelling consumer credit risk via survival analysis , 2009 .