Aplicación del Modelo Media Varianza con Machine Learning para Optimización de Portafolios de Inversión
DOI:
https://doi.org/10.31637/epsir-2025-1844Palabras clave:
Portafolio de Inversión, Rentabilidad, Volatilidad, Modelo Media Varianza, Machine Learning, Simulación Montecarlo, Portafolio óptimo, Frontera EficienteResumen
Introducción: La optimización de portafolios de inversión busca encontrar el conjunto óptimo de activos que maximicen la rentabilidad bajo un nivel de riesgo determinado. Este estudio propone el uso del Modelo de Media Varianza (MMV), combinado con la regresión LASSO y la Simulación Monte Carlo, para optimizar un portafolio en el mercado colombiano. Metodología: Se utilizaron datos históricos de acciones y TES del periodo 2015 a 2023. Primero, se aplicó el MMV para identificar portafolios eficientes, luego la regresión LASSO para seleccionar activos clave y, finalmente, la Simulación Monte Carlo para evaluar escenarios y construir carteras óptimas. Resultados: El portafolio óptimo está compuesto por TES (37,65%), Grupo Energía Bogotá (23,35%), Nutresa (20,71%), ISA (10,63%) y Bancolombia (7,67%). La rentabilidad del portafolio óptimo es 0,010123%, y su volatilidad es 0,762192%. Discusión y Conclusiones: El estudio destaca la importancia de combinar técnicas computacionales con modelos clásicos para optimizar portafolios en mercados emergentes. Se concluye que el MMV, junto con Machine Learning y la Simulación Monte Carlo, es adecuado para optimizar portafolios y maximizar los beneficios en un nivel de riesgo determinado.
Descargas
Citas
Al-Muharraqi, M. y Messaadia, M. (2023). Implementing Machine Learning in Optimizing Stock Portfolios: A review. 2023 International Conference On Cyber Management And Engineering (CyMaEn), 500-504. https://doi.org/10.1109/CyMaEn57228.2023.10051023 DOI: https://doi.org/10.1109/CyMaEn57228.2023.10051023
Ban, G. Y., Karoui, N. y Lim, A. (2018). Machine Learning and Portfolio Optimization. Manag. Sci., 64, 1136-1154. https://doi.org/10.1287/mnsc.2016.2644 DOI: https://doi.org/10.1287/mnsc.2016.2644
Basuki, B., Sukono, S., Sofyan, D., Madio, S. y Puspitasari, N. (2019). Linear Algebra on investment portfolio optimization model. Journal of Physics: Conference Series, 1402. https://doi.org/10.1088/1742-6596/1402/7/077089 DOI: https://doi.org/10.1088/1742-6596/1402/7/077089
Botero, S. B., García-Mazo, C. M. y Arboleda-Moreno, F. J. (2024). Power generation mix in Colombia including wind power: Markowitz portfolio efficient frontier analysis with machine learning. Journal of Open Innovation: Technology, Market, and Complexity, 10(4). https://doi.org/10.1016/j.joitmc.2024.100402 DOI: https://doi.org/10.1016/j.joitmc.2024.100402
Chang, X. (2022). The application of the Full Markowitz Model in generating optimal investment portfolio. 2022 2nd International Conference on Management Science and Industrial Economy Development (MSIED 2022). https://doi.org/10.23977/msied2022.040
Chen, S. (2022). Research on investment portfolio strategy based on intelligent optimization algorithm. Proceedings of the 11th International Conference on Software and Information Engineering. https://doi.org/10.1145/3571513.3571526 DOI: https://doi.org/10.1145/3571513.3571526
Chen, W., Zhang, H., Mehlawat, M., y Jia, L. (2021). Mean-variance portfolio optimization using machine learning-based stock price prediction. Appl. Soft Comput., 100, 106943. https://doi.org/10.1016/j.asoc.2020.106943 DOI: https://doi.org/10.1016/j.asoc.2020.106943
Chen, Y., Lu, H., Yu, T., Chao, X., Tao, X., Zeng, L., Gorskiy, M., Tarasyuk, Y., Wang, Q., Dong, L., Safitri, I. N., Sudradjat, S., Lesmana, E., N.V., N. A., Hoang, V. T., Alkindi, F., Sadalia, I., Muda, I., Zhang, X., … Soltani, R. (2024). Analysis of Optimal Stock Portfolio Investment on The LQ45 Index Using the Markowitz Model and Single Index Model. BCP Business & Management, 1, 47-58. https://doi.org/10.23977/msied2022.040 DOI: https://doi.org/10.23977/MSIED2022.040
Chen, Z. (2024). Research on Portfolio Optimization Model based on Machine Learning Algorithm in Stock Market. Transactions on Economics, Business and Management Research. https://doi.org/10.62051/sdqv4p21 DOI: https://doi.org/10.62051/sdqv4p21
Feng, Q. (2022). Optimal Portfolio Construction Based on Markowitz Model. BCP Business & Management. https://doi.org/10.54691/bcpbm.v35i.3303 DOI: https://doi.org/10.54691/bcpbm.v35i.3303
García, C. M. y Moreno, J. A. (2011). Optimización de portafolios de pensiones en Colombia: el esquema de multifondos, 2003-2010. Ecos de Economía, 15(33), 139-183.
Grupo Aval. (2024). Renta Fija - Tes. Grupo Aval. https://acortar.link/QO4bi7
Hauck, K. y Woutersen, T. (2024). Explaining Ridge Regression and LASSO (pp. 1-17). Advances in Econometrics. https://acortar.link/BbhR7T
Hu, Y. (2024). Portfolio Optimization Using Machine Learning Method and Monte Carlo Simulation. Highlights in Business, Economics and Management. https://doi.org/10.54097/farx3k44 DOI: https://doi.org/10.54097/farx3k44
Jerončić, M., y Aljinović, Z. (2011). Forming the optimal portfolio based on the markowitz model with diversification of companies by sectors. Ekonomski Pregled, 62(9-10), 583-606. https://acortar.link/4d4qcB
Kaplan, P. D., y Savage, S. (2011). Markowitz 2.0. In Frontiers of Modern Asset allocation (pp. 325-349). https://doi.org/10.1002/9781119205401.ch26 DOI: https://doi.org/10.1002/9781119205401.ch26
Kobets, V. y Savchenko, S. (2022). Building an Optimal Investment Portfolio with Python Machine Learning Tools. Information Technology and Implementation, 307-315. https://ceur-ws.org/Vol-3347/Short_1.pdf
Markowitz, H. (1952). PORTFOLIO SELECTION. The Journal of Finance, 7(1), 77-91. https://doi.org/10.1111/j.1540-6261.1952.tb01525.x DOI: https://doi.org/10.1111/j.1540-6261.1952.tb01525.x
Martínez-Sánchez, J. F., Cruz-García, S. y López-Castillo, J. I. (2021). Optimización de un portafolio con Python. Pädi Boletín Científico de Ciencias Básicas e Ingenierías Del ICBI, 9(17), 132-135. https://doi.org/10.29057/icbi.v9i17.6807 DOI: https://doi.org/10.29057/icbi.v9i17.6807
Ossa González, G. A. (2023). Comparación de los modelos de Black-Litterman, Markowitz y CAPM en la estimación de los rendimientos esperados en el mercado de renta variable en Colombia. Revista Estrategia Organizacional, 12(2), 29-53. https://doi.org/10.22490/25392786.7230 DOI: https://doi.org/10.22490/25392786.7230
Padhi, D., Padhy, N., Bhoi, A., Shafi, J. y Yesuf, S. H. (2022). An Intelligent Fusion Model with Portfolio Selection and Machine Learning for Stock Market Prediction. Computational Intelligence and Neuroscience. https://doi.org/10.1155/2022/7588303 DOI: https://doi.org/10.1155/2022/7588303
Paiva, F., Cardoso, R., Hanaoka, G. y Duarte, W. (2019). Decision-making for financial trading: A fusion approach of machine learning and portfolio selection. Expert Syst. Appl., 115, 635–655. https://doi.org/10.1016/j.eswa.2018.08.003 DOI: https://doi.org/10.1016/j.eswa.2018.08.003
Rodríguez-Marín, L. V. (2018). SELECCIÓN DE UNA CARTERA DE ACCIONES DEL ÍNDICE COLCAP EN EL CORTO PLAZO; MEDIANTE LA EVALUACIÓN DEL MODELO DE MEDIA- VARIANZA, EL MODELO GRAHAM Y UN FONDO BURSÁTIL DE INVERSIÓN [UNIVERSIDAD CATÓLICA DE PEREIRA].
https://catalogo.ucp.edu.co/cgi-bin/koha/opac-detail.pl?biblionumber=561413
Saranya, K. y Prasanna, P. K. (2014). Portfolio Selection and Optimization with Higher Moments: Evidence from the Indian Stock Market. Asia-Pacific Financial Markets, 21(2), 133-149. https://doi.org/10.1007/s10690-014-9180-0 DOI: https://doi.org/10.1007/s10690-014-9180-0
Syahla, R., Susanti, D. y Napitupulu, H. (2024). Optimization of Investment Portfolio Mean-Variance Model Using Genetic Algorithm. International Journal of Business, Economics, and Social Development. https://doi.org/10.46336/ijbesd.v5i2.654 DOI: https://doi.org/10.46336/ijbesd.v5i2.654
Wang, Q. (2023). Optimizing Stock Portfolio using Markowitz Model. BCP Business & Management. https://doi.org/10.54691/bcpbm.v44i.4926 DOI: https://doi.org/10.54691/bcpbm.v44i.4926
Yao, L. (2023). APPLICATION OF THE MARKOWITZ MODEL AND INDEXMODEL IN REAL STOCK MARKETS. Finance & Economics. https://doi.org/10.61173/ypyp5r05 DOI: https://doi.org/10.61173/ypyp5r05
Yilin, Han, R., y Wang, W. (2021). Portfolio optimization with return prediction using deep learning and machine learning. Expert Syst. Appl., 165, 113973. https://doi.org/10.1016/j.eswa.2020.113973 DOI: https://doi.org/10.1016/j.eswa.2020.113973
Zhang, X. (2024). Application and Comparison of Index Model and Markowitz Model in American Stock Market. Highlights in Business, Economics and Management. https://doi.org/10.54097/snr61486 DOI: https://doi.org/10.54097/snr61486
Zhou, S. y Zhang, S. (2023). Portfolio Optimization Analysis in American Industry. BCP Business & Management. https://doi.org/10.54691/bcpbm.v38i.4213 DOI: https://doi.org/10.54691/bcpbm.v38i.4213
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 Claudia María García Mazo
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Non Commercial, No Derivatives Attribution 4.0. International (CC BY-NC-ND 4.0.), that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
