Cooperative coevolution of feed forward neural networks for financial time series problem

Abstract

Intelligent financial prediction systems guide investors in making good investments. Investors are continuously on the hunt for better financial prediction systems. Neural networks have shown good results in the area of financial prediction. Cooperative coevolution is an evolutionary computation method that decomposes the problem into subcomponents and has shown promising results for training neural networks. This paper presents a computational intelligence framework for financial prediction where cooperative coevolutionary feedforward neural networks are used for predicting closing market prices for companies listed on the NASDAQ stock exchange. Problem decomposition is an important step in cooperative coevolution that affects its performance. Synapse and Neuron level are the main problem decomposition methods in cooperative coevolution. These two methods are used for training neural networks on the given financial prediction problem. The results show that Neuron level problem decomposition gives better performance in general. A prototype of a mobile application is also given for investors that can be used on their Android devices.

A Survey on Evolutionary Construction of Deep Neural Networks

“…1) EAs are suitable for training DNNs with small size, such as RNNs and DBNs. For example, in [21]- [24], EAs are applied to train the RNN, where direct encoding is used to represent model parameters and the cooperative coevolution is used as the search paradigm. Because of the global search nature of EAs, the models trained by EAs achieve better performance than the ones trained by the gradient-based methods.…”

“…2) Cooperative Co-Evolution: In this framework, the model parameters are decomposed into several groups where each group is optimized by the EA in a separate but cooperative way. Finally, the optimal model parameters found in each group are combined to produce the solutions [21]- [24]. In [22], two approaches were proposed to decompose model parameters, i.e., synapse based and neuron based, where groups correspond to the single connection weight and all connection weights for a neuron, respectively.…”

Neuron-Network Level Problem Decomposition Method for Cooperative Coevolution of Recurrent Networks for Time Series Prediction

“…Sunspot RBF with orthogonal least squares (2006) [15] 4.60E-02 Locally linear neuro-fuzzy model (2006) [15] 3.20E-02 SL-CCRNN [3] 1.66E-02 1.47E-03 NL-CCRNN [3] 2.60E-02 3.62E-03 FNN-NSL [7] 1.33E-02 5.38E-04 Proposed RNN-NNL 1.89E-02 1.90E-03 ACI FNN-SL [16] 1.92E-02 Worldwide FNN-NL [16] 1.91E-02 MO-CCFNN-T=2 [17] 1.94E-02 MO-CCFNN-T=3 [17] 1.47E-02 Neuron-Synapse Level method FNN-NSL [7] better methods will be needed to cater for the chaotic nature of the time series problems at certain time intervals.…”