Seleção de carteiras de investimento usando DEA

• Ano de defesa: 2023
• Autor(a) principal: Massareli, Éverton
• Orientador(a): Sandoval, Wilfredo Sosa
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Católica de Brasília
• Programa de Pós-Graduação: Programa Stricto Sensu em Economia de Empresas
• Departamento: Escola de Humanidades, Negócios e Direito
• País: Brasil
• Palavras-chave em Português: Carteira de investimentos; Análise envoltória de dados; Mercado acionário brasileiro
• Palavras-chave em Inglês: Fund portfolios; Data envelopment analysis; Brazilian stock market
• Área do conhecimento CNPq: CNPQ::CIENCIAS SOCIAIS APLICADAS::ECONOMIA
• Link de acesso: https://bdtd.ucb.br:8443/jspui/handle/tede/3202

This study aims to demonstrate a new practical alternative for creating investment fund portfolios using data envelopment analysis - DEA, from the non-parametric model of Banker, Charnes and Cooper [1]. Having the variation in the quotation of the assets, we can assemble a portfolio with the greatest efficiency and the maximum return possible for the assets studied, in comparison with the modern portfolio theory of Markowitz (1952) [2]. The outputs will be the exponential of the arithmetic mean of the returns of each asset, an increasing, convex, and differentiable function to keep the same order and the inputs will be the quotient of the exponential of the expected return divided by the standard deviation. When applying the DEA, the portfolio will be built among the "𝑁" assets subdivided among the "𝑀" groups, not necessarily uniform. The criteria for calculating the efficient portfolio will be to choose the assets with the highest efficiency from each group and those with the lowest correlation of two assets at a predefined value. This study intends to increase the diversity of the methodology for optimal choices of investment fund portfolios. The methodology was applied to 20 financial assets listed on B3 (former Bovespa).