Application of a hierarchical coevolutionary fuzzy system for financial prediction and trading

In this paper, the application of a hierarchical coevolutionary fuzzy system called HiCEFS for predicting financial time series is investigated. A novel financial trading system using the HiCEFS as a predictive model and employing a prudent trading strategy based on the price percentage oscillator (PPO) is proposed. In order to construct an accurate predictive model, a form of generic membership function named Irregular Shaped Membership Function (ISMF) is employed and a hierarchical coevolutionary genetic algorithm (HCGA) is adopted to automatically derive the ISMFs for each input variable in HiCEFS. With the accurate prediction from HiCEFS and a prudent trading strategy, the proposed financial trading system outperforms the simple buy-and-hold strategy, the trading system without prediction and the trading system with other predictive models (EFuNN, DENFIS and RSPOP) on real-world financial data.