International Journal of Modern Physics and Applications
Articles Information
International Journal of Modern Physics and Applications, Vol.1, No.3, Jul. 2015, Pub. Date: Jun. 24, 2015
Embedding Dimension as Input Dimension of Artificial Neural Network: A Study on Stock Prices Time Series
Pages: 64-72 Views: 4575 Downloads: 1560
Authors
[01] Amir Hosein Ghaderi, Neuroscience Lab., University of Tabriz, Tabriz, Iran.
[02] Bahar Barani, Medical School, University of Kansas, Kansas City, USA.
[03] Hoda Jalalkamali, Neuroscience Lab., University of Tabriz, Tabriz, Iran.
Abstract
Recently artificial neural networks (ANNs) have become crucial for the analysis of several phenomena in the world. Stock market prices is a nonlinear phenomenon that several studies are accomplished in this context using ANN. Determine the input dimension of network is a basic problem in application of ANN to prediction of stock prices. On the other hand, stock market behaves as a chaotic system with nonlinear and deterministic manner. Therefore chaos theory can be helpful to determine the input dimension of network. In this study a multilayer perceptron with Backpropagation learning algorithm is used for forecasting of stock prices in Tehran Stock Exchange (TSE). Prediction accuracy of ANN with various input dimensions is compared and the best result is achieved when the input dimension is equal to Takens embedding dimension. It is concluded that selection of Takens embedding as ANN input dimension can be led to very accurate predictions and best results in TSE.
Keywords
Neural Network, Chaos Theory, Multilayer Perceptron, Embedding Dimension, Stock Market, Forecasting
References
[01] Peters EE. A chaotic attractor for the SP 500. Financial Analysts Journal, 1991:55-81.
[02] Qian B, Rasheed K. Stock market prediction with multiple classifiers. Applied Intelligence 2007;2 6 (1):25-33.
[03] Shively PA. The nonlinear dynamics of stock prices. The Quarterly Review of Economics and Finance 2003; 43 (3):505-17.
[04] Huang SC, Chuang PJ, Wu CF, Lai HJ. Chaos-based support vector regressions for exchange rate forecasting. Expert Systems with Applications 2010; 3 7(12):8590-98.
[05] Kao LJ, Chiu CC, Lu CJ, Yang JL. Integration of nonlinear independent component analysis and support vector regression for stock price forecasting. Neurocomputing. 2013; 99:53442.
[06] Kazem A, Sharifi E, Hussain FK, Saberi M, Hussain OK. Support vector regression with chaos-based firefly algorithm for stock market price forecasting. Applied Soft Computing 2013; 13: 94758.
[07] Wang YF. Predicting stock price using fuzzy grey prediction system. Exspert Systems with Applications 2002; 22(1):33-38.
[08] Naik RL, Ramesh D, Manjula B, Govardhan A. Prediction of Stock Market Index Using Genetic Algorithm. Computer Engineering and Intelligent Systems 2012; 3(7):162-71.
[09] Shaverdi M, Fallahi S, Bashiri V. Prediction of Stock Price of Iranian Petrochemical Industry Using GMDH-Type Neural Network and Genetic algorithm. Applied Mathematical Sciences 2012; 6(7):319-32.
[10] Esfahanipour A, Aghamiri W. Adapted neuro-fuzzy inference system on indirect approach TSK fuzzy rule base for stock market analysis. Expert Systems with Applications 2010; 37(7):4742-48.
[11] Liu CF, Yeh CY, Lee SJ. Application of type-2 neuro-fuzzy modeling in stock price prediction. Applied Soft Computing, 2012; 12(4):1348-58.
[12] Ghaderi AH, Darooneh AH. ARTIFICIAL NEURAL NETWORK WITH REGULAR GRAPH FOR MAXIMUM AIR TEMPERATURE FORECASTING: THE EFFECT OF DECREASE IN NODES DEGREE ON LEARNING. International Journal of Modern Physics C 2012; 23 (02):1-10.
[13] Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 2003; 50: 159-75.
[14] Ardalani-Farsa M, Zolfaghari S. Chaotic time series prediction with residual analysis method using hybrid Elman-NARX neural networks. Neurocomputing 2010; 73(13):2540-53.
[15] Hen HY, Hwang JN. Handbook of neural network signal processing. CRC press, 2010.
[16] Senjyu T, Miyazato H, Yokoda S, Uezato K. Speed control of ultrasonic motors using neural network. Power Electronics, IEEE Transactions on 1998; 13(3):381-87.
[17] Ghaderi F. Ghaderi AH, Najafi B, Ghaderi N. Viscosity Prediction by Computational Method and Artificial Neural Network Approach: The Case of Six Refrigerants. The Journal of Supercritical Fluids 2013; 81: 6778.
[18] Kohzadi N, Boyd MS, Kermanshahi B, Kaastra I. A comparison of artificial neural network and time series models for forecasting commodity prices. Neurocomputing 1996; 10 (2):169-81.
[19] Wood D, Dasgupta B. Classifying trend movements in the MSCI USA capital market indexa comparison of regression, ARIMA and neural network methods. Computers Operations Research 1996; 23 (6):611-22.
[20] Yao J, Tan CL, Poh HL. Neural networks for technical analysis: a study on KLCI. International journal of theoretical and applied finance 1999:2(02):221-41. 9.
[21] Kaastra I, Boyd M. Designing a neural network for forecasting financial and economic time series. Neurocomputing 1996; 10(3):215-36.
[22] Huang W, Lai KK, Nakamori Y, Wang S, Yu L. Neural networks in finance and economics forecasting. International Journal of Information Technology Decision Making 2007; 6 (01):113-40.
[23] Castiglione F. Forecasting price increments using an artificial Neural Network. Advances in Complex Systems 2001;4(01):45-56
[24] Cao Q, Leggio KB, Schniederjans MJ. A comparison between Fama and French’s model and artificial neural networks in predicting the Chinese stock market. Computers Operations Research 2005; 32 (10):2499-512.
[25] Roman J, Jameel A. (1996, January). Backpropagation and recurrent neural networks in financial analysis of multiple stock market returns. In System Sciences, 1996, Proceedings of the Twenty-Ninth Hawaii International Conference on, IEEE (Vol. 2, pp. 454-460).
[26] Khoa NLD, Sakakibara K, Nishikawa I. Stock price forecasting using back propagation neural networks with time and profit based adjusted weight factors. In SICE-ICASE International Joint Conference, IEEE 2006 (pp. 5484-5488).
[27] Wah BenjaminW, Minglun Qian. ”Constrained formulations and algorithms for stock-price predictions using recurrent FIR neural networks.” PROCEEDINGS OF THE NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE. Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press; 1999, 2002.
[28] Kim KJ, Han I. Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert systems with applications 2000; 19 (2):125-32.
[29] Leigh W, Purvis R, Ragusa JM. Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural network, and genetic algorithm: a case study in¡ i¿ romantic¡/i¿ decision support. Decision Support Systems 2002; 32 (4):361-77.
[30] Du P, Luo X, He Z, Xie L. The application of genetic algorithm-radial basis function (ga-rbf) neural network in stock forecasting. In Control and Decision Conference (CCDC), IEEE 2010 Chinese (pp. 1745-1748).
[31] Zhang Y,Wu L. Stock market prediction of SP 500 via combination of improved BCO approach and BP neural network. Expert systems with applications, 2009; 36 (5):8849-54.
[32] Shen W, Guo X, Wu C, Wu D. Forecasting stock indices using radial basis function neural networks optimized by artificial fish swarm algorithm. Knowledge-Based Systems 2011;24 (3):378-85
[33] Hsieh T, HF Hsiao, WC Yeh. Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm. Applied Soft Computing 2011;11: 251025
[34] Lu CJ, Wu JY. An e_cient CMAC neural network for stock index forecasting. Expert Systems with Applications 2011;38(12):15194-201
[35] Hadavandi E, Shavandi H, Ghanbari A. Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowledge-Based Systems 2010; 23 (8):800-8.
[36] Sheng Z, Hong-Xing L, Dun-Tang G, Si-Dan D. Determining the input dimension of a neural network for nonlinear time series prediction. Chinese Physics 2003; 12 (6):594.
[37] Takens F. Dynamical systems and turbulence. Lecture notes in mathematics 1981; 898 (9):366.
[38] Grassberger P, Procaccia I. Measuring the strangeness of strange attractors. Physica D: Nonlinear Phenomena 1983; 9 (1):189-208.
[39] Oh KJ, Kim KJ. Analyzing stock market tick data using piecewise nonlinear model. Expert Systems with Applications 2002;22(3):249-55
[40] Steeb WH. The Nonlinear Workbook, World Scientific, New York, 2005.
[41] Dreyfus G. Neural Networks: Methodology and Applications, Springer, Berlin, 2005.
[42] Fausett L. Fundamentals of Neural Networks, Prentice Hall, NJ, 1994.
600 ATLANTIC AVE, BOSTON,
MA 02210, USA
+001-6179630233
AIS is an academia-oriented and non-commercial institute aiming at providing users with a way to quickly and easily get the academic and scientific information.
Copyright © 2014 - American Institute of Science except certain content provided by third parties.