Finance time series prediction using complex-valued flexible neural tree model

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).

[1]  D. Brillinger.  Time series - data analysis and theory , 1981, Classics in applied mathematics.

[2]  Dervis Karaboga,et al.  A comprehensive survey: artificial bee colony (ABC) algorithm and applications , 2012, Artificial Intelligence Review.

[3]  Zhiping Lin,et al.  Predicting time series with wavelet packet neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[4]  Musa Peker,et al.  A new approach for automatic sleep scoring: Combining Taguchi based complex-valued neural network and complex wavelet transform , 2016, Comput. Methods Programs Biomed..

[5]  Yuehui Chen,et al.  Reverse engineering of gene regulatory networks using flexible neural tree models , 2013, Neurocomputing.

[6]  Jiwen Dong,et al.  Time-series forecasting using flexible neural tree model , 2005, Inf. Sci..

[7]  Samir K. Safi,et al.  A Comparison of Artificial Neural Network and Time Series Models for Forecasting GDP in Palestine , 2016 .

[8]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[9]  Herman Eerens,et al.  Image time series processing for agriculture monitoring , 2014, Environ. Model. Softw..

[10]  Weimin Ma,et al.  Study on stock price prediction based on BP Neural Network , 2010, 2010 IEEE International Conference on Emergency Management and Management Sciences.

[11]  Mauricio Kugler,et al.  An Approach for Sound Source Localization by Complex-Valued Neural Network , 2013, IEICE Trans. Inf. Syst..

[12]  B. Bowerman,et al.  Forecasting and Time Series: An Applied Approach , 2000 .

[13]  Dhiya Al-Jumeily,et al.  Regularized dynamic self-organized neural network inspired by the immune algorithm for financial time series prediction , 2016, Neurocomputing.

[14]  Yüksel Özbay,et al.  Fuzzy clustering complex-valued neural network to diagnose cirrhosis disease , 2011, Expert Syst. Appl..

[15]  Byungwhan Kim,et al.  Modeling of ion energy distribution using time-series neural network , 2008, ICONS 2008.

[16]  Yuehui Chen,et al.  Hybrid-Learning Methods for Stock Index Modeling , 2006 .

[17]  Kazuyuki Murase,et al.  Single-layered complex-valued neural network for real-valued classification problems , 2009, Neurocomputing.

[18]  Dervis Karaboga,et al.  Artificial Bee Colony (ABC) Optimization Algorithm for Solving Constrained Optimization Problems , 2007, IFSA.

[19]  Ponnuthurai N. Suganthan,et al.  Random vector functional link network for short-term electricity load demand forecasting , 2016, Inf. Sci..