Genetic Programming for Financial Trading : a Tutorial
Abstract
Genetic Programming (GP) is an appealing machine-learning technique for tackling financial engineering problems: it belongs to the family of evolutionary algorithms that have proven to be often remarkably successful at handling complex optimization problems, and possesses the unique feature to produce solutions under a symbolic form that can be understood and analyzed by humans. Over the last decade, numerous studies have investigated the use of GP for creating financial trading strategies. We will first provide a comprehensive review of existing work and identify stylized facts about trading returns and trading behaviour that can be drawn from the literature. We will then discuss practical implementation issues. Finally, we will present a series of pretests, similar in the spirit to pretests in econometrics, aimed at giving clear-cut answers on whether GP can be effective with the time series at hand. We conclude by highlighting directions for future work.