Optimization of asset portfolios using metaheuristics Evolution Strategy
DOI:
https://doi.org/10.22478/ufpb.2318-1001.2023v11n2.64883Abstract
Objective: to develop an optimization program, using the Evolution Strategy (ES) metaheuristic, to assist investors in decision making regarding the selection of long-term investment portfolios.
Background: metaheuristics, in general, are applied to solve very complex optimization problems, where an optimal solution is not necessarily the goal, but a set of good solutions.
Method: The algorithm employs fundamental analysis to analyze and determine the stocks that will compose the asset portfolios. To achieve the proposed objective, the study was based on a historical series of companies listed on B3 in the period of 2018 and the portfolio returns were estimated through the asset pricing model (CAPM). To verify the program's ability to generate good results, the estimated returns were compared with the real returns calculated in the years 2018 to 2020 and also with the Bovespa index (benchmark).
Results: The results generated by the program were satisfactory, since the real returns of the selected portfolios were higher than the estimated returns, and both were higher than the Ibovespa.
Contributions: the work presents contributions in the field of personal finance, for the individual by proposing more profitable portfolio options, and consequently, increasing their equity in the long term and contributes to the economic development of the country, therefore, the provision of reliable tools, which give support investment decisions, tends to attract more investors and more financial resources for companies to invest in their growth, generating employment and income.
Downloads
References
Adebiyi A., & Ayo, C. (2015). Portfolio selection problem using generalized differential evolution 3. Applied Mathematical Sciences, 9(42), 2069–2082.
Adebiyi, M. O., Adebiyi, A. A., Obagbuwa, C. I., & Okesola, J. O. (2019). A comparative study of metaheuristics techniques for portfolio selection problem. Journal of Engineering and Applied Sciences, 14, 2007-2010.
Araújo, R. L. F., & Maia, S. F. (2011). O papel da análise fundamentalista na formação de uma carteira de ações para investimentos: um estudo empírico nas empresas que compõem o índice imobiliário da BM&FBovespa. Anais do ENEX/PROBEX. UFPB, João Pessoa, PB.
Ardia, D., Boudt, K., Carl, P., Mullen, K.M., & Peterson, B.G. (2011). Differential evolution with DEoptim: an application to non-convex portfolio optimization. The R. Journal, 3(1), 27-34.
Assaf Neto, A. (2016). Finanças Corporativas e Valor. São Paulo: Atlas.
B3. (2020). B3 divulga estudo sobre o perfil dos investidores pessoa física na bolsa. Disponível em: https://www.b3.com.br/pt_br/noticias/pessoa-fisica.htm
B3. (2021). B3 atinge 4 milhões de contas em renda variável. Disponível em: https://www.b3.com.br/pt_br/noticias/4-milhoes-de-pfs.htm
Barros, T. S. (2015). Análise técnica e fundamentalista: ensaios sobre os métodos de análise. Revista de Administração e Negócios da Amazônia, 7(2), 39-63.
Beiruth, A. X., Fiorot, H. F., Scalzer, R. S., & Lima, V. S. (2007). Análise fundamentalista e avaliação de empresas: uma investigação teórica e um estudo de caso na Aracruz Celulose. Artigo apresentado no X Fórum de Ciências Contábeis do Espírito Santo. Aracruz.
Beneish, M. D., Lee, C. M. C., & Tarpley, R. L. (2001). Contextual fundamental analysis through the prediction of extreme returns. Review of Accounting Studies, 6(2–3), 165–189.
Beyer, H-G., & Schwefel, H-P. (2002). Evolution strategies: a comprehensive introduction. Natural Computing , 1(1), 3-52.
Cherobim, A. P. M. S. (2014). Mercado de Capitais. UFPR, Curitiba.
CVM (2017). Análise de investimentos: histórico, principais ferramentas e mudanças conceituais para o futuro. Associação de Analistas e Profissionais de Investimentos no Mercado de Capitais - APIMEC; Comissão de Valores Mobiliários. Rio de Janeiro: CVM. Disponível em: www.cvm.gov.br
Damodaran, A. (2017). Avaliação de Investimentos: ferramentas e técnicas para a determinação do valor de qualquer ativo. 6º ed. Rio de Janeiro: Qualitymark.
Dinheirama. Valuation e alguns indicadores fundamentalistas. Disponível em: https://dinheirama.com/valuation-e-alguns-indicadores-fundamentalistas/
Di Tollo, G., & Roli, A. (2008). Metaheuristics for the portfolio selection problem. International Journal Operational Research,5(1), 13–35.
Doering, J., Kizys, R., Juan, A. A., Fitó, A., & Polat, O. (2019). Metaheuristics for rich portfolio optimisation and risk management: current state and future trends. Research Perspectives, 6.
Donega, P. H. C. C., Lima, N. C., Souza, G. H. S., & Silva, C. L. (2020). Análise da precificação de ações em empresas agropecuárias da B3. IGepec, Toledo, 24(2),30-52.
Ertenlice, O., & Kalayci, C.B. (2018). A survey of swarm intelligence for portfolio optimization: algorithms and applications. Swarm and Evolutionary Computation, 39, 36–52.
Etchegaray, A. A. (2021). Portfolio optimization using evolutionary algorithms. Dissertation, Universidade Nova de Lisboa.
Ewald, R., Schulz, R., & Uhrmacher, A. M. (2010). Selecting simulation algorithm portfolios by genetic algorithms. IEEE Workshop on Principles of Advanced and Distributed Simulation, 1-9.
Fonseca, C. M., & Fleming, P. J. (1995). An overview of evolutionary algorithms in multiobjective optimization. Evolutionary Computation, 3(1),1–16, Spring.
Gilli, M., & Schumann, E. (2010). Heuristic Optimisation in Financial Modelling. Annals of Operations Research, Forthcoming.
Guerreiro, A. P. (2018). Portfolio selection in evolutionary algorithms. Doctoral, Faculty of Sciences and Technology of the University of Coimbra. http://hdl.handle.net/10316/87398
GUIAINVEST. Checklist: os 11 critérios fundamentalistas para avaliações de ações. Disponível em: https://www.guiainvest.com.br/download/checklist-analise-guiainvest.pdf
Hoklie & Zuhal, L. R. (2010). Resolving multi objective stock portfolio optimization problem using genetic algorithm. The 2nd International Conference on Computer and Automation Engineering (ICCAE), Singapore, 40-44.
InfoMoney. Indicadores fundamentalistas: guia para analisar empresas listadas. Disponível em: https://www.infomoney.com.br/guias/indicadores-fundamentalistas/
Invest Exame. Estes são 4 indicadores importantes da análise fundamentalista. Disponível em: https://invest.exame.com/academy/4-indicadores-importantes-analise-fundamentalista/
Kerr, R. B. (2011). Mercado financeiro e de capitais. São Paulo: Pearson.
Kolm, P.N., Tütüncü, R., & Fabozzi, F.J. (2014). 60 years of portfolio optimization: practical challenges and current trends. European Journal Operational Research, 234(2),356–71.
Lai, K. K, Yu, L., Wang, S., & Zhou, C. (2006). A Double-stage genetic optimization algorithm for portfolio selection. In: King, I. et al. (Ed.). Neural Information Processing: Springer Berlin/Heidelberg, 928-937.
Lambora, A., Gupta, K., & Chopra, K. (2019). Genetic Algorithm- A Literature Review. International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India, 380-384.
Lim, S., Kim, M., & Ahn, C. W. (2020). A genetic algorithm (GA) approach to the portfolio design based on market movements and asset valuations. in IEEE Access, 8, 140234-140249.
Lima Jr., M. P., Almeida, M. R., & Ferreira, R. J. P. (2011). Seleção de portfólios por meio de busca tabu híbrida: modelo de média variância em lotes. XLIII Simpósio Brasileiro de Pesquisa Operacional, Ubatupa SP.
Lin, C.C., & Liu, Y.T. (2008). Genetic algorithms for portfolio selection problems with minimum transaction lots. European Journal Operational Research, 185, 393-404.
Liu W-h. (2017). Optimal computing budget allocation to the differential evolution algorithm for large-scale portfolio optimization. Journal Simulation, 11(4), 380–90.
Lwin, K., Qu, R., & Kendall, G. (2014). A learning-guided multi-objective evolutionary algorithm for constrained portfolio optimization. Applied Soft Computing Journal, 24, 757–772.
Ma, X., Gao, Y., & Wang, B. (2012). Portfolio optimization with cardinality constraints based on hybrid differential evolution. AASRI Procedia, 1, 311–7.
Malta, T. L., & Camargos, M. A. (2016). Variáveis da análise fundamentalista e dinâmica e o retorno acionário de empresas brasileiras entre 2007 e 2014. REGE - Revista de Gestão, 23, 52–62.
Milhomem, D. A. (2020). Seleção de portfólio de ações por meio de otimização metaheurística híbrida com redes neurais LSTM. Dissertação (mestrado), Pontifícia Universidade Católica de Goiás. http://tede2.pucgoias.edu.br:8080/handle/tede/4512
Mishra, S.K., Panda, G., & Majhi, R. (2014). Constrained portfolio asset selection using multiobjective bacteria foraging optimization. Operational Research, 14(1), 113–45.
Nichols, D. C. & Wahlen, J. M. (2004). How do earnings numbers relate to stockreturns? A review of classic accounting research with updated evidence. Accounting Horizons, 18(4), 263–286.
Piotroski, J. D. (2005). Discussion of “separating winners from losers amonglow book-to-market stocks using financial statement analysis”. Review of Accounting Studies, 10(2-3), 171–184.
Qu, B. Y., Zhou, Q. , Xiao, J. M., Liang, J. J., & Suganthan, P. N. (2017). Large-scale portfolio optimization using multiobjective evolutionary algorithms and preselection methods, Mathematical Problems in Engineering, 1-14.
Russo, L. M. S., & Francisco, A. P. (2014). Quick hypervolume. IEEE Transactions on Evolutionary Computation, 18(4), 481–502.
Singh, A., & Kumar, S. (2016). Differential evolution: an overview. In book: Proceedings of Fifth International Conference on Soft Computing for Problem Solving, 209-217.
Skolpadungket, P., Dahal, K., & Harnpornchai, N. (2007). Portfolio optimization using multiobjective genetic algorithms. IEEE Congress on Evolutionary Computation, Singapore, 516-523.
Streichert, F., & Yamawaki, M.T. (2006). The effect of local search on the constrained portfolio selection problem. In: Evolutionary Computation, IEEE Congress on, 2368-2374.
Strumberger, I., Bacanin, N., & Tuba, M. (2016). Constrained portfolio optimization by hybridized bat algorithm. 7th International conference on intelligent systems, modelling and simulation (ISMS). IEEE, 83–88.
Tang, G. Y. (2004). How efficient is naive portfolio diversification? An educational note. Omega, 32(2), 155–160.
Tofighian, A.A., Moezzi, H., Barfuei, M.K., & Shafiee, M. (2018). Multi-period project portfolio selection under risk considerations and stochastic income. Journal Industrial Engineering International, 14(3), 571–84.
Tuba, M., & Bacanin, N. (2014). Artificial bee colony algorithm hybridized with firefly algorithm for cardinality constrained mean-variance portfolio selection problem. Applied Mathematics and Information Sciences, 8(6), 2831.
Urli, B., & Terrien, F. (2010). Project portfolio selection model, a realistic approach. International Transactions in Operational Research, 17(6), 809–26.
Vijayalakshmi Pai G-A., & Michel T. (2014). Metaheuristic multi-objective optimization of constrained futures portfolios for effective risk management. Swarm and Evolutionary Computation, 19, 1–14.
Yang, Xin-She. (2020). Nature-inspired optimization algorithms. 2ºEd., Academic Press.
Yevseyeva, I., Guerreiro, A. P., Emmerich, M. T. M., & Fonseca, C. M. (2014). A portfolio optimization approach to selection in multiobjective evolutionary algorithms. In T. Bartz-Beielstein et al., editors, Parallel Problem Solving from Nature — PPSN XIII, volume 8672 of Lecture Notes in Computer Science, 672–681. Springer International Publishing.
Zhang, G., & Chen, P. (2007). How do accounting variables explain stock pricemovements? Theory and evidence. Journal of Accounting and Economics, 43(2), 219–244.
Zhang, H., & Yan, C. (2018). Modelling fundamental analysis in portfolio selection. Quantitative Finance, 18(8), 1315-1326.
Zhang, W. G., Chen, W., & Wang, Y., L. (2006). The adaptive genetic algorithms for portfolio selection problem. International Journal Computer Science and Network Security, 6, 196-200.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Revista Evidenciação Contábil & Finanças
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autores que publicam na RECFin concordam com os seguintes termos:- Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho simultaneamente licenciado sob a Licença Creative Commons Attribution que permite o compartilhamento do trabalho com reconhecimento da autoria e publicação inicial nesta revista;
- Em virtude de aparecerem nesta revista de acesso público, os artigos são de uso gratuito, com atribuições próprias, em aplicações educacionais e não-comerciais;
- A revista permitirá o uso dos trabalhos publicados para fins não-comerciais, incluindo direito de enviar o trabalho para bases de dados de acesso público.
