Geometric Semantic Genetic Programming for Financial Data

摘要

We cast financial trading as a symbolic regression problem on the lagged time series, and test a state of the art symbolic regression method on it. The system is geometric semantic genetic programming, which achieves good performance by converting the fitness landscape to a cone landscape which can be searched by hill-climbing. Two novel variants are introduced and tested also, as well as a standard hill-climbing genetic programming method. Baselines are provided by buy-and-hold and ARIMA. Results axe promising for the novel methods, which produce smaller trees than the existing geometric semantic method. Results are also surprisingly good for standard genetic programming. New insights into the behaviour of geometric semantic genetic programming are also generated.