A portfolio optimization model with three objectives and discrete variables

We formulate the portfolio selection as a tri-objective optimization problem so as to find tradeoffs between risk, return and the number of securities in the portfolio. Furthermore, quantity and class constraints are introduced into the model in order to limit the proportion of the portfolio investe...

Full description

Saved in:
Bibliographic Details
Published in:Computers & operations research 2010-07, Vol.37 (7), p.1285-1297
Main Authors: Anagnostopoulos, K.P., Mamanis, G.
Format: Article
Language:English
Subjects:
Applied sciences
Approximation
Class constraints
Comparative analysis
Decision theory. Utility theory
Evolutionary multiobjective optimization
Exact sciences and technology
Genetic algorithms
Hierarchies
Integer programming
Multiobjective portfolio selection
NSGA-II
Operational research and scientific management
Operational research. Management science
Optimization techniques
PESA
Portfolio investments
Portfolio theory
Quantity constraints
SPEA2
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We formulate the portfolio selection as a tri-objective optimization problem so as to find tradeoffs between risk, return and the number of securities in the portfolio. Furthermore, quantity and class constraints are introduced into the model in order to limit the proportion of the portfolio invested in assets with common characteristics and to avoid very small holdings. Since the proposed portfolio selection model involves mixed integer decision variables and multiple objectives finding the exact efficient frontier may be very hard. Nevertheless, finding a good approximation of the efficient surface which provides the investor with a diverse set of portfolios capturing all possible tradeoffs between the objectives within limited computational time is usually acceptable. We experiment with the current state of the art evolutionary multiobjective optimization techniques, namely the Non-dominated Sorting Genetic Algorithm II (NSGA-II), Pareto Envelope-based Selection Algorithm (PESA) and Strength Pareto Evolutionary Algorithm 2 (SPEA2), for solving the mixed-integer multiobjective optimization problem and provide a performance comparison among them using metrics proposed by the community.
ISSN:0305-0548
1873-765X
0305-0548
DOI:10.1016/j.cor.2009.09.009