Genetic relation algorithm with guided mutation for the large-scale portfolio optimization

Chen, Yan; Mabu, Shingo; Hirasawa, Kotaro

doi:10.1016/j.eswa.2010.08.120

Cited by 26 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To test the second hypothesis, genetic algorithm (Holland, 1992, Chen et al, 2011 is run based on the Markowitz model observing the stability of the algorithm, then the results of the optimum portfolio formation were evaluated using genetic algorithms. To do so, the run algorithm was iterated 10 times and the answers obtained from tests were compared.…”

Section: Second Hypothesis`s Test Resultsmentioning

confidence: 99%

Comparative evaluation of fuzzy logic and genetic algorithms models for portfolio optimization

Soureh¹,

Amanollahi²

2017

10.5267/j.msl

View full text Add to dashboard Cite

Selection of optimum methods which have appropriate speed and precision for planning and decision-making has always been a challenge for investors and managers. One the most important concerns for them is investment planning and optimization for acquisition of desirable wealth under controlled risk with the best return. This paper proposes a model based on Markowitz theorem by considering the aforementioned limitations in order to help effective decisionsmaking for portfolio selection. Then, the model is investigated by fuzzy logic and genetic algorithms, for the optimization of the portfolio in selected active companies listed in Tehran Stock Exchange over the period 2012-2016 and the results of the above models are discussed. The results show that the two studied models had functional differences in portfolio optimization, its tools and the possibility of supplementing each other and their selection.

show abstract

Section: Second Hypothesis`s Test Resultsmentioning

confidence: 99%

Comparative evaluation of fuzzy logic and genetic algorithms models for portfolio optimization

Soureh¹,

Amanollahi²

2017

10.5267/j.msl

View full text Add to dashboard Cite

show abstract

“…El proceso de maximización del rendimiento de inversión para los activos financieros de estudio se realizó mediante Algoritmos Genéticos de acuerdo con Chen et al (2011) y Ding et al (2020.…”

Section: Desarrollo Del Algoritmo Genéticounclassified

Trading a través del indicador RSI con la aplicación de Algoritmos Genéticos para la implementación en el sector empresarial de las inversiones

2022

View full text Add to dashboard Cite

Objetivo: Este artículo propone para la literatura sobre inversión de activos de renta variable una metodología aplicada a través de Algoritmos Genéticos (AG) y su implementación en el sector empresarial de inversión. Método: El estudio se desarrolló mediante simulación de las estrategias de inversión B&H, AT y AG sobre el índice accionario. El proceso de maximización del rendimiento de inversión para los activos financieros se realizó mediante Algoritmos Genéticos, los cuales se basaron en ecuaciones definidas en la tipificación cromosómica con operaciones inmersas en los genes. Se inició con una población aleatoria de individuos con cromosomas representando una solución para lograr el mayor rendimiento posible. Resultados: La aplicación de algoritmos con el RSI generó rendimientos superiores al 9 y 16% respecto a B&H y el análisis técnico, lo que quiere decir, mayor riesgo de inversión para B&H con volatilidad 17,6% pero comparable a las exhibidas por algoritmos genéticos y análisis técnico. Conclusiones: Mejor relación rendimiento-riesgo y eficiencia en los parámetros fundamentales de la Teoría de Portafolio es posible a través de estrategias de inversión basadas en algoritmos genéticos incluyendo el oscilador RSI. Este estudio sugiere que un mejoramiento del rendimiento de inversión puede ser anticipado mediante los parámetros stop loss y take profit y un rango de movimiento del precio del activo previo la toma de posición.

show abstract

“…Chen et al [16] proposed a time adapting genetic network programming model which was able to cope with the temporal behavior of asset prices. Chen et al [17] employed the genetic relation algorithm and considered the correlation coefficient between stock brands as the edges in a graph structure to pick up the most efficient portfolio. Michell et al [18] proposed a combination of the fuzzy inference system and strongly typed genetic programming to improve the efficiency of the genetic programming techniques.…”

Section: Related Workmentioning

confidence: 99%

Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning

Taghian¹,

Asadi²,

Safabakhsh³

2020

Preprint

View full text Add to dashboard Cite

Generating asset-specific trading signals based on the financial conditions of the assets is one of the challenging problems in automated trading. Various asset trading rules are proposed experimentally based on different technical analysis techniques. However, these kind of trading strategies are profitable, extracting new asset-specific trading rules from vast historical data to increase total return and decrease the risk of portfolios is difficult for human experts. Recently, various deep reinforcement learning (DRL) methods are employed to learn the new trading rules for each asset. In this paper, a novel DRL model with various feature extraction modules is proposed. The effect of different input representations on the performance of the models is investigated and the performance of DRL-based models in different markets and asset situations is studied. The proposed model in this work outperformed the other state-of-theart models in learning single asset-specific trading rules and obtained a total return of almost 262% in two years on a specific asset while the best state-ofthe-art model get 78% on the same asset in the same time period.

show abstract

Genetic relation algorithm with guided mutation for the large-scale portfolio optimization

Cited by 26 publications

References 24 publications

Comparative evaluation of fuzzy logic and genetic algorithms models for portfolio optimization

Comparative evaluation of fuzzy logic and genetic algorithms models for portfolio optimization

Trading a través del indicador RSI con la aplicación de Algoritmos Genéticos para la implementación en el sector empresarial de las inversiones

Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning

Contact Info

Product

Resources

About