Examinando por Materia "portfolio optimization"
Mostrando 1 - 4 de 4
Resultados por página
Opciones de ordenación
Ítem Desarrollo de una interfaz gráfica para la implementación de modelos de optimización robusta de portafolios(Universidad Eafit, 2020) González Guatibonza, José Nicolás; Laniado Rodas, HenryThis research work addresses the problem of optimization of asset portfolios by making an initial approach to the classic optimization models derived from "Portfolio Selection*" (1952), the pioneering work of Henry Markowitz, covering the models of mean and minimal variance along with the equally weighted investment distribution model. From the investigation of their weaknesses, a new approach is made to those that propose the use of robust statistical estimators and the elimination of outliers in the time series involved in the optimization process, including the use of the minimum determinant algorithm of the covariance matrix (Fast-MCD) and that of a new statistical estimator of such matrix by means of a shrinkage to its sample form and the application of a model that involves the use of the comedian as a statistically robust estimator of the matrix, which is object of a subsequent shrinkage process. Next, the development of a graphical user interface on Matlab numerical computing software is presented, which implements the models studied and offers an interactive means of learning and performance analysis, thus leaving a precedent for developing software open to future improvements and investigative uses.Ítem Forecasting stock return using a recurrent neural network apply to a financial optimization problem(Universidad EAFIT, 2021) Ochoa Ramírez, Juliana; Almonacid Hurtado, Paula MariaThis paper presents a methodological proposal for optimizing financial asset portfolios by incorporating the returns predictions instead of the historical returns to calculate an efficient frontier. We changed the return means methodology to forecast by the return with LSTM neural network. We performed several simulation exercises to evaluate the methodology with real data from the US stock market to examine our portfolio optimization model. To evaluate our results, we compared the mean-variance frontier efficiency with the neural network return model. We selected one optimal portfolio that offered the highest expected return for a defined level of risk and compare both models. We show how the neural network return model has a better performance for different periods of time, outperforming the mean-variance model at the same level.Ítem Investment portfolio optimization with transaction costs through a multiobjective genetic algorithm: an applied case to the Colombian Stock Exchange(Universidad Icesi, 2018-01-01) De Greiff, Samuel; Carlos Rivera, Juan; Universidad EAFIT. Escuela de Ciencias; Modelado MatemáticoThis paper discusses portfolio optimization by considering constraints imposed by financial markets and conditions of projects with excess liquidity, such as transaction costs, limited budget and short time planning horizons. In light of these constraints, conventional models are found to generate non-efficient portfolios. Consequently, a mathematical model is formulated and a multiobjective genetic algorithm is implemented in order to find efficient portfolios in the Colombian Stock Exchange (Bolsa de Valores de Colombia), minimizing risks and maximizing profits. In addition, results are shown which allow comparison between those portfolios obtained through the proposed model and the mean-variance model, highlighting the importance of transaction costs and budget in investment decision making.Ítem Investment portfolio optimization with transaction costs through a multiobjective genetic algorithm: an applied case to the Colombian Stock Exchange(Universidad Icesi, 2018-01-01) De Greiff, Samuel; Carlos Rivera, Juan; De Greiff, Samuel; Carlos Rivera, Juan; Universidad EAFIT. Departamento de Ciencias; Matemáticas y AplicacionesThis paper discusses portfolio optimization by considering constraints imposed by financial markets and conditions of projects with excess liquidity, such as transaction costs, limited budget and short time planning horizons. In light of these constraints, conventional models are found to generate non-efficient portfolios. Consequently, a mathematical model is formulated and a multiobjective genetic algorithm is implemented in order to find efficient portfolios in the Colombian Stock Exchange (Bolsa de Valores de Colombia), minimizing risks and maximizing profits. In addition, results are shown which allow comparison between those portfolios obtained through the proposed model and the mean-variance model, highlighting the importance of transaction costs and budget in investment decision making.