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

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