Examinando por Autor "Bodas, Diego"

Mostrando 1 - 4 de 4

A technique for the optimization of the parameters of technical indicators with multi-objective evolutionary algorithms
(IEEE, 2012-06-10) Bodas, Diego; Soltero, Francisco José; Fernández, Pablo; Hidalgo, José Ignacio
Technical indicators (TIs) are used to interpret stock market and to predict market trends. The main difficulty in the use of TIs lies in deciding which their optimal parameter values are in each moment, since constant optimal values do not seem to exist. In this work, the use of Multi-Objective Evolutionary Algorithms (MOEAs) is proposed to obtain the best values of the parameters in order to help to buy and sell shares. Those parameters are applied in real time and belong to a collection of indicators. Unlike other previous approaches, the necessity of repeating the parameter optimization process each time a new data enters the system is justified, searching for the best adjustment of the parameters (and hence the TIs) in every moment. The Moving Averages Convergence-Divergence (MACD) indicator and the Relative Strength Index (RSI) oscillator have been chosen as TIs, so the MOEAs will provide the best parameters to use them on investment decisions. Experiments compare up to nine different configurations with the Buy & Hold strategy (B & H). The obtained results show that the Multi-Objective technique proposed here can greatly improve the results of the B & H strategy even operating daily. This statement is also demonstrated by comparing the results to those previously presented in the literature.
Clasificadores inductivos para el posicionamiento web
(EPI SCP, Barcelona, Spain, 2012-06-28) Soltero, Francisco José; Bodas, Diego
En este trabajo se muestra cómo el estudio individual de los distintos atributos básicos de un recurso web no es suficiente para inferir las distintas estrategias de posicionamiento de un motor de búsqueda. El problema fundamental que se plantea es cuál es la relación entre los distintos elementos que componen la página y el peso que cada uno de ellos aporta al posicionamiento final. Como alternativa a este problema se propone la utilización de técnicas de aprendizaje inductivo, más concretamente, clasificadores arbóreos. Los resultados se ven reflejados en dos experimentos, fruto de la aplicación de dos algoritmos de aprendizaje distintos. Como resultado final se observa que la aplicación de esta técnica puede ser un punto de partida muy interesante para la optimización del posicionamiento web.
Multiobjective optimization of technical market indicators
(Association for Computing Machinery New York, NY, United States, 2009-07-12) Bodas, Diego; Fernández, Pablo; Hidalgo, José Ignacio; Soltero, Francisco; Risco, José Luis
This paper deals with the optimization of technical indicators for stock market investment. Price prediction is a problem of great complexity and usually some technical indicators are used to predict the markets trends. The main difficulty in the use of technical indicators lies in deciding the parameters values. We proposed the use of Evolutionary Algorithms (EAs) to obtain the best parameter values belonging to a collection of indicators that will help in the buying and selling of shares. This paper extends the work presented on previous works by including additional indicators and applying them to more complex problems. In this way the Moving Averages Convergence-Divergence (MACD) indicator and the Relative Strength Index (RSI) oscillator have been selected to obtain the buying/selling signals. The experimental results indicate that our EAs offer a solution to the problem obtaining results that improve those obtained through technical indicators with their standard parameters.
Optimization of technical indicators in real time with multiobjective evolutionary algorithms
(Association for Computing Machinery New York, NY, United States., 2012-07-07) Soltero, Francisco José; Bodas, Diego; Fernández, Pablo; Hidalgo, José Ignacio
Technical analysis uses technical indicators to identify changes in market trend. These are composed by a set of parameters and rules, whose values try to determine the future movements of the assets. This paper addresses the optimization of these values depending on the current market, allowing better returns with less risk. The use of Multi-objective Evolutionary Algorithms (MOEAs) is proposed in this work to obtain the best parameter values in real time belonging to a collection of indicators that will help in the buying and selling of shares. Unlike other previous approaches, the necessity of repeating the parameters optimization process each time a new data enters the system is justified, searching for the best adjustment in every moment. This technique can greatly improve the results of Buy & Hold (B & H) strategy even operating daily. This statement will be demonstrated by comparing the results to those presented in the literature.