Evolution of trading strategies with flexible structures: A configuration comparison

Martín, Carlos; Quintana, David; Isasi, Pedro

doi:10.1016/j.neucom.2018.11.062

Cited by 2 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionsupporting

confidence: 60%

“…Giving support in the first instance to our results on the profitability of learned trading rules over B&H strategies, the study by Martín et al (2018) on the generation of trading rules based on technical indicators for the S&P 500 through a methodology based on the refinements of GA showed that the B&H can reasonably be beaten by the implemented GP strategy. However, Martín et al 's (2018) study time-dependency of the algorithm performances was also evidenced. The referred dependency trait from the use of the GA-based approaches showed generated rules in the range 78–90.5% in cases of either improving or beating the B&H. Given the relatively short timeframe of our dataset for analysis (2013–2017) compared to that analyzed in Martín et al (2018), we may infer that more than the time-dependency commonly observed in Martín et al (2018) the outperformance of the index during the timeframe of our study may presumably play a determinant role in the algorithm learning process and supported the effects on maximizing our function ( returns ), and consequently, had a positive impact mostly on the GA-based approach over the alternatives B&H and technical only.…”

Section: Discussionsupporting

confidence: 60%

“…the outperformance of the index during the timeframe of our study may presumably play a determinant role in the algorithm learning process and supported the effects on maximizing our function ( returns ), and consequently, had a positive impact mostly on the GA-based approach over the alternatives B&H and technical only. Furthermore, the extent of any time-dependency (if any) could probably not be entirely unveiled because of the constrained dataset length under our study compared with Martín et al 's (2018) study.…”

Section: Discussionmentioning

confidence: 90%

“…However, Martín et al 's (2018) study time-dependency of the algorithm performances was also evidenced. The referred dependency trait from the use of the GA-based approaches showed generated rules in the range 78–90.5% in cases of either improving or beating the B&H. Given the relatively short timeframe of our dataset for analysis (2013–2017) compared to that analyzed in Martín et al (2018), we may infer that more than the time-dependency commonly observed in Martín et al (2018) the outperformance of the index during the timeframe of our study may presumably play a determinant role in the algorithm learning process and supported the effects on maximizing our function ( returns ), and consequently, had a positive impact mostly on the GA-based approach over the alternatives B&H and technical only. the outperformance of the index during the timeframe of our study may presumably play a determinant role in the algorithm learning process and supported the effects on maximizing our function ( returns ), and consequently, had a positive impact mostly on the GA-based approach over the alternatives B&H and technical only.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Artificial intelligence applied to investment in variable income through the MACD (moving average convergence/divergence) indicator

Aguirre

Méndez

Medina

2021

JEFAS

View full text Add to dashboard Cite

PurposeThis study aims to determine whether, by means of the application of genetic algorithms (GA) through the traditional technical analysis (TA) using moving average convergence/divergence (MACD), is possible to achieve higher yields than those that would be obtained using technical analysis investment strategies following a traditional approach (TA) and the buy and hold (B&H) strategy.Design/methodology/approachThe study was carried out based on the daily price records of the NASDAQ financial asset during 2013–2017. TA approach was carried out under graphical analysis applying the standard MACD. GA approach took place by chromosome encoding, fitness evaluation and genetic operators. Traditional genetic operators (i.e. crossover and mutation) were adopted as based on the chromosome customization and fitness evaluation. The chromosome encoding stage used MACD to represent the genes of each chromosome to encode the parameters of MACD in a chromosome. For each chromosome, buy and sell indexes of the strategy were considered. Fitness evaluation served to defining the evaluation strategy of the chromosomes in the population according to the fitness function using the returns gained in each chromosome.FindingsThe paper provides empirical-theoretical insights about the effectiveness of GA to overcome the investment strategies based on MACD and B&H by achieving 5 and 11% higher returns per year, respectively. GA-based approach was additionally capable of improving the return-to-risk ratio of the investment.Research limitations/implicationsLimitations deal with the fact that the study was carried out on US markets conditions and data which hamper its application in some extend to markets with not as much development.Practical implicationsThe findings suggest that not only skilled but also amateur investors may opt for investment strategies based on GA aiming at refining profitable financial signals to their advantage.Originality/valueThis paper looks at machine learning as an up-to-date tool with great potential for increasing effectiveness in profits when applied into TA investment approaches using MACD in well-developed stock markets.

show abstract

Section: Discussionsupporting

confidence: 60%

Section: Discussionsupporting

confidence: 60%

Section: Discussionmentioning

confidence: 90%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence applied to investment in variable income through the MACD (moving average convergence/divergence) indicator

Aguirre

Méndez

Medina

2021

JEFAS

View full text Add to dashboard Cite

show abstract

“…Figure 10 Performing a sample decoding in GE [60] The purpose and main cycle are basically the same as standard GP, but they differ in the way that solutions are created and updated [61]. Figure 10 shows an example of decoding with GE.…”

Section: Grammar Evolution (Ge)mentioning

confidence: 99%

A Review of Genetic Programming: Popular Techniques, Fundamental Aspects, Software Tools and Applications

Ari

Alagöz

2021

Sakarya University Journal of Science

View full text Add to dashboard Cite

Genetic Programming (GP) is one of the evolutionary computation (EC) methods followed with great interest by many researchers. When GP first appeared, it has become a popular computational intelligence method because of its successful applications and its potentials to find effective solutions for difficult practical problems of many different disciplines. With the use of GP in a wide variety of areas, numerous variants of GP methods have emerged to provide more effective solutions for computation problems of diverse application fields. Therefore, GP has a very rich literature that is progressively growing. Many GP software tools developed along with process of GP algorithms. There is a need for an inclusive survey of GP literature from the beginning to today of GP in order to reveal the role of GP in the computational intelligence field. This survey study aims to provide an overview of the growing GP literature in a systematic way. The researchers, who need to implement GP methods, can gain insight of potentials in GP methods, their essential drawbacks and prevalent superiorities. Accordingly, taxonomy of GP methods is given by a systematic review of popular GP methods. In this manner, GP methods are analyzed according to two main categories, which consider the discrepancies in their program (chromosome) representation styles and their methodologies. Besides, GP applications in diverse problems are summarized. This literature survey is especially useful for new researchers to gain the required broad perspective before implementing a GP method in their problems.

show abstract

Evolution of trading strategies with flexible structures: A configuration comparison

Cited by 2 publications

References 41 publications

Artificial intelligence applied to investment in variable income through the MACD (moving average convergence/divergence) indicator

Artificial intelligence applied to investment in variable income through the MACD (moving average convergence/divergence) indicator

A Review of Genetic Programming: Popular Techniques, Fundamental Aspects, Software Tools and Applications

Contact Info

Product

Resources

About