Back to search

Democritus University of Thrace (DUTH)

Financial portfolio optimization using multiobjective evolutionary algorithms

Abstract

dc:description

This thesis focuses particularly on financial portfolio optimization problems using multiobjective evolutionary algorithms. The thesis is organized in eight chapters: seven chapters consisting of the main results of our research and a final chapter named Epilogue which contains a summary of the main results of this work, and outlines some ideas and further directions for future research. Each chapter of this thesis has been extracted from autonomous research papers. Chapter 1 provides an overview of the main portfolio selection models with complex constraints and/or multiple objectives and surveys the literature on the use of multiobjective metaheuristics (MOMHs) applied in complex portfolio optimization problems. Chapter 2 investigates the ability and compares the effectiveness of state-of-the-art multiobjective evolutionary algorithms (MOEAs), to solve complex portfolio optimization problems. Chapter 3 considers a mean-variance portfolio optimization model extended to include class, cardinality and quantity constraints. This chapter proposes a novel, generalized form of class constraints that both limit the proportion of the portfolio invested in certain classes and impose lower and up-per bounds on the number of classes that the portfolio is being "exposed”. Three of the main MOEAs with a problem specific data structure for chromosome representation and specialized variation operators are implemented. Chapter 4 compares the effectiveness of state-of-the-art MOEAs together with a steady-state evolutionary algorithm on the mean-variance cardinality constrained portfolio optimization problem (MVCCPO). Chapter 5 solves different constrained mean-risk portfolio optimization models using a recently developed simulated annealing-based multiobjective optimization algorithm. Chapter 6 formulates 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. The problem is solved using state-of-the-art multiobjective evolutionary algorithms. Chapter 7 considers a large-scale three-objective mean-variance-skewness portfolio selection model with additional real-world constraints which limit the number of assets in the portfolio and the amount invested in these assets. The problem is solved using the best multiobjective evolutionary algorithm, namely SPEA2.

Degree

thesis:*
Grantor dc:publisher
Democritus University of Thrace (DUTH)
Year dc:date
2012

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Mamanis, Georgios
  • Μαμάνης, Γεώργιος

Subjects

dc:subject × 12

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/28430

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Mamanis, Georgios; Μαμάνης, Γεώργιος. Financial portfolio optimization using multiobjective evolutionary algorithms. Democritus University of Thrace (DUTH), 2012. http://hdl.handle.net/10442/hedi/28430