Efficient Portfolio Construction with the Use of Multiobjective Evolutionary Algorithms: 
Best Practices and Performance Metrics

Abstract

This paper provides a systematic study of the technologies and algorithms associated with the 
implementation of multiobjective evolutionary algorithms (MOEAs) for the solution of the portfolio 
optimization problem. Based on the examination of the state-of-the art we provide the best practices 
for dealing with the complexities of the constrained portfolio optimization problem (CPOP). 
In particular, rigorous algorithmic and technical treatment is provided for the efficient incorporation 
of a wide range of real-world constraints into the MOEAs. Moreover, we address special configuration 
issues related to the application of MOEAs for solving the CPOP. Finally, by examining the 
state-of-the-art we identify the most appropriate performance metrics for the evaluation of the relevant 
results from the implementation of the MOEAs to the solution of the CPOP.