A Comparative Study of Technical Trading Strategies Using a Genetic Algorithm

Abstract

Traditional approaches to the study of technical analysis (TA) often focus on the performance of a single indicator, which seems to fall short in scope and depth. We use a genetic algorithm (GA) to optimize trading strategies in the three major Forex markets, in order to verify the adequacy of TA strategies and rules to attain consistent superior returns, by comparing momentum, trend and breakout indicators. The indicators with the parameters generated through our GA consistently outperform the equivalent indicators applying parameters commonly used by the trading industry. EUR/USD and GBP/USD markets present interesting return figures before trading costs. The inclusion of spreads and commissions deteriorates returns substantially, suggesting these markets, under a more realistic set of assumptions, may be efficient. Trend indicators generate better outcomes and GBP/USD qualifies as the most profitable market. Different aggregate returns in different markets may stand as evidence of distinct maturation stages under an evolving efficiency market perspective. Our GA is able to search a wider solution space than traditional configurations and presents the possibility of recovering latent data, avoiding premature convergence.

Analyzing the Impact of Strategic Behavior in an Evolutionary Learning Model Using a Genetic Algorithm

“…Where experimental data verify changes in actions, surroundings, and decision-making, such social trends remain resilient and difficult to alter, according to the study, offering insights into how to impact social development. Macedo et al (2020) applied a Genetic Algorithm to optimize trading strategies, which outperformed the analyzed market indicators by employing a more comprehensive search space than traditional methods.…”

Stock Movement Modeling Based on the Analysis of Negative Correlation

“…Researchers also adopted other learning algorithms to predict stocks including decision tree induction [20], [21], genetic algorithm [22]- [24], state space modeling [25], and optimization techniques [26]. To improve predictive accuracy of the induced models, many researchers considered a fusion approach that combined results from model ensemble such as a hybrid adaptive neuro inference system [27], a bagging of tree-based classifiers [28], [29], an integrated forecasting system using wavelet neural network and artificial bee colony [30], a deep learning approach incorporated with two-directional principal component analysis [31], and support vector machine integrated with probabilistic AdaBoost [32].…”

Mean-semivariance portfolio optimization with multiobjective evolutionary algorithms and technical analysis rules

“…Several studies present strong evidence in favour of TA, either based on indicator analysis, such as (Brock, Lakonishok, & LeBaron, 1992) and (Pinto, Neves, & Horta, 2015), or based on chart analysis, like (Lo, Mamaysky, & Wang, 2000). However, other studies, such as (Allen & Karjalainen, 1999) and (Neely, 2003), acknowledge little value in TA-based strategies; this is particularly so when some more realistic assumptions -like the existence of transaction costs -are considered (Macedo, Godinho, & Alves, 2016). In this context, it is important to gather further empirical evidence for or against the validity of TA as an effective tool to exploit market inefficiencies, namely in stock markets.…”