Finance time series prediction using complex-valued flexible neural tree model
Bin Yang, Wei Zhang, Lina Gong, Huaizhi Ma · 2017
In this paper, we present a novel time series prediction model based on complex-valued flexible neural tree (CVFNT) model to improve the forecasting accuracy. In a CVFNT model, data, parameters and activation functions are complex-valued. The evolutionary method based on the modified genetic algorithm (GP) and artificial bee colony (ABC) is used to evolve the CVFNT model. Two real time series datasets from Shanghai stock index and exchange rates between Euro and US Dollar are used to test CVFNT model. Results reveal that our proposed method can predict more accurately finance time series than real-valued classic neural networks (RVNN) and complex-valued neural network (CVNN).