Portfolio Optimization Using Evolutionary Algorithms

Detalhes bibliográficos
Autor(a) principal: Etchegaray, Alejandro Alvarez
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/119447
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics
id RCAP_5d3b58bb75a77523e47f3d1805a1ceaa
oai_identifier_str oai:run.unl.pt:10362/119447
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Portfolio Optimization Using Evolutionary AlgorithmsPortfolio optimizationGenetic AlgorithmDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced AnalyticsPortfolio optimization is a widely studied field in modern finance. It involves finding the optimal balance between two contradictory objectives, the risk and the return. As the number of assets rises, the complexity in portfolios increases considerably, making it a computational challenge. This report explores the application of the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) and Genetic Algorithm (GA) in the field of portfolio optimization. MOEA/D and GA have proven to be effective at finding portfolios. However, it remains unclear how they perform when compared to traditional approaches used in finance. To achieve this, a framework for portfolio optimization is proposed, using MOEA/D, and GA separately as optimization algorithms and Capital Asset Pricing Model (CAPM) and Mean-Variance Model as methods to evaluate portfolios. The proposed framework is able to produce weighted portfolios successfully. These generated portfolios were evaluated using a simulation with subsequent (unseen) prices of the assets included in the portfolio. The simulation was compared with well known portfolios in the same market and other market benchmarks (Security Market Line and Market Portfolio). The results obtained in this investigation exceeded expectation by creating portfolios that perform better than the market. CAPM and Mean-Variance Model, although they fail to model all the variables that affect the stock market, provide a simple valuation for assets and portfolios. MOEA/D using Differential Evolution operators and the CAPM model produced the best portfolios in this research. Work can still be done to accommodate more variables that can affect markets and portfolios, such as taxes, investment horizon and costs for transactions.Castelli, MauroRUNEtchegaray, Alejandro Alvarez2021-06-17T15:31:20Z2021-06-072021-06-07T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/119447TID:202734528enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:02:02Zoai:run.unl.pt:10362/119447Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:44:05.710951Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Portfolio Optimization Using Evolutionary Algorithms
title Portfolio Optimization Using Evolutionary Algorithms
spellingShingle Portfolio Optimization Using Evolutionary Algorithms
Etchegaray, Alejandro Alvarez
Portfolio optimization
Genetic Algorithm
title_short Portfolio Optimization Using Evolutionary Algorithms
title_full Portfolio Optimization Using Evolutionary Algorithms
title_fullStr Portfolio Optimization Using Evolutionary Algorithms
title_full_unstemmed Portfolio Optimization Using Evolutionary Algorithms
title_sort Portfolio Optimization Using Evolutionary Algorithms
author Etchegaray, Alejandro Alvarez
author_facet Etchegaray, Alejandro Alvarez
author_role author
dc.contributor.none.fl_str_mv Castelli, Mauro
RUN
dc.contributor.author.fl_str_mv Etchegaray, Alejandro Alvarez
dc.subject.por.fl_str_mv Portfolio optimization
Genetic Algorithm
topic Portfolio optimization
Genetic Algorithm
description Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics
publishDate 2021
dc.date.none.fl_str_mv 2021-06-17T15:31:20Z
2021-06-07
2021-06-07T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/119447
TID:202734528
url http://hdl.handle.net/10362/119447
identifier_str_mv TID:202734528
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138049136787456

Registros relacionados