Abstract

This paper presents an approach to single-position, intra-day automated trading based on a neuro-genetic algorithm. An Artificial Neural Network (ANN) is developed to provide trading signals to a very unsophisticated automated trading agent, while the evolutionary algorithm is defined in order to optimize neural network design, by performing a joint evolution of neural network weights and topology. Experimental results indicate that, despite its simplicity, both in terms of input data and in terms of trading strategy, such an approach to automated trading may yield significant returns.