Evaluation of co-evolutionary neural network architectures for time series prediction with mobile application in finance

Abstract

The fusion of soft computing methods such as neural networks and evolutionary algorithms have given a very promising performance for time series prediction problems. In order to fully harness their strengths for wider impact, effective real-world implementation of prediction systems must incorporate the use of innovative technologies such as mobile computing. Recently, co-evolutionary algorithms have shown to be very promising for training neural networks for time series prediction. Cooperative coevolution decomposes a problem into subcomponents that are evolved in isolation and cooperation typically involves fitness evaluation. The challenge has been in developing effective subcomponent decomposition methods for different neural network architectures. In this paper, we evaluate the performance of two problem decomposition methods for training feedforward and recurrent neural networks for chaotic time series problems. We further apply them for financial prediction problems selected from the NASDAQ stock exchange. We highlight the challenges in real-time implementation and present a mobile application framework for financial time series prediction. The results, in general, show that recurrent neural networks have better generalisation ability when compared to feedforward networks for real-world time series problems.