A Proposal of Stock Price Predictor Using Associated Memory

Shigeki Nagaya; Zhang Chenli; Osamu Hasegawa

doi:10.20965/jaciii.2011.p0145

single-jc.php

« previous

JACIII Vol.15 No.2 pp. 145-155

doi: 10.20965/jaciii.2011.p0145

(2011)

Paper:

Views over last 60 days: 645

A Proposal of Stock Price Predictor Using Associated Memory

Shigeki Nagaya, Zhang Chenli, and Osamu Hasegawa

Imaging Science and Engineering Laboratory, Tokyo Institute of Technology, 4259 Nagatsuta, Midori-ku, Yokohama 226-8503, Japan

Received:

April 16, 2010

Accepted:

January 24, 2011

Published:

March 20, 2011

Keywords:

associated memory, self-organizing incremental neural network (SOINN), signal prediction, casebased reasoning

Abstract

The novel method [1] we propose for predicting stock prices is a case-based reasoning predictor based on associative stock price data memory using Self-Organizing and IncrementalNeural Networks (SOINN) [2]. When a user inputs stock price data, the predictor outputs the most likely prediction based on statistically summarizing similar stock price pattern. It also outputs all cases included in the prediction. Our method has following advantages: (a) our predictor gives users grounds by giving all cases consisting of the prediction using associative memory. Users thereby recognize and are ready for prediction risk. (b) Our predictor avoids large prediction failures because it modifies itself through online learning and continues to learn without its learning parameters being reassigned. This makes it much safer where investment loss may be large. (c) Our predictor is as profitable as previous work while realizing unique, useful functions, as shown by experimental results using actual stock price data from the US and Japan markets between 1998 and 2005.

Cite this article as:

S. Nagaya, Z. Chenli, and O. Hasegawa, “A Proposal of Stock Price Predictor Using Associated Memory,” J. Adv. Comput. Intell. Intell. Inform., Vol.15 No.2, pp. 145-155, 2011.

Data files:

References

[1] S. Nagaya, Z. Chenli, and O. Hasegawa, “An Associated-memorybased Stock Price Predictor,” Int. Conf. on Artificial Neural Networks, Vol.2, pp. 345-357, 2009.
[2] F. Shen and O. Hasegawa, “An incremental network for on-line unsupervised classification and topology learning,” Neural Networks, Vol.19, No.1, pp. 90-106, 2006.
[3] E. F. Fama, “Efficient Capital Markets: A Review of Theory and Empirical Work,” The J. of Finance, Vol.25, No.2, pp. 383-417, 1970.
[4] K. Schierholt and C. H. Dagli, “Stock market prediction using different neural network classification architectures,” IEEE/IAFE Conf. on Computational Intelligence for Financial Engineering, pp. 72-78, 1996.
[5] P. K. H. Phua, Z. Xiaotian, and H. K. Chung, “Forecasting stock index increments using neural networks with trust region methods,” Int. Joint Conf. on Neural Networks, Vol.1, pp. 260-265, 2003.
[6] P. D. Yoo, M. H, Kim, and T. Jan, “Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation,” Int. Conf. on Computational Intelligence for Modelling, Control and Automation and Intelligent Agents, Web Technologies and Internet Commerce, Vol.2, pp. 835-841, 2005.
[7] C. Lu, “Integrating independent component analysis-based denoising scheme with neural network for stock price prediction,” Expert Systems with Applications Vol.37, pp. 7056-7064, 2010.
[8] H. Li, C. H. Dagli, and D. Enke, “Forecasting Series-based Stock Price Data Using Direct Reinforcement Learning,” Int. Joint Conf. on Neural Networks, Vol.2, pp. 1103-1108, 2004.
[9] T. Matsui and H. Ohwada, “A Reinforcement Learning Agent for Stock Trading: An Evaluation,” The 20th Annual Conf. of the Japanese Society for Artificial Intelligence, Vol.20, pp. 3C1-6, 2006.
[10] M. Matsumoto, K. Fukui, K. Moriyama, S. Kurihara, and M. Numao, “A Design and Evaluation of Q-learning Agents on U-Mart,” The 20th Annual Conf. of the Japanese Society for Artificial Intelligence, 2006.
[11] H. Li, C. H. Dagli, and D. Enke, “Short-term Stock Market Timing Prediction under Reinforcement Learning Schemes,” IEEE Int. Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 233-240, 2007.
[12] J.W. Lee, “Stock Price Prediction Using Reinforcement Learning,” IEEE Int. Symposium on Industrial Electronics, Vol.1, pp. 690-695, 2001.
[13] A. Sudo, A. Sato, and O. Hasegawa, “Associative Memory for Online Incremental Learning in Noisy Environments,” Int. Joint Conf. on Neural Networks, Vol.12, No.17, pp. 619-624, 2007.
[14] S. Okada and O. Hasegawa, “Incremental Learning, Recognition, and Generation of Time-Series Patterns Based on Self-Organizing Segmentation,” J. of Advanced Computational Intelligence and Intelligent Informatics,Vol.10, No.3, pp. 395-408, 2006.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] S. Nagaya, Z. Chenli, and O. Hasegawa, “An Associated-memorybased Stock Price Predictor,” Int. Conf. on Artificial Neural Networks, Vol.2, pp. 345-357, 2009.

[2] [2] F. Shen and O. Hasegawa, “An incremental network for on-line unsupervised classification and topology learning,” Neural Networks, Vol.19, No.1, pp. 90-106, 2006.

[3] [3] E. F. Fama, “Efficient Capital Markets: A Review of Theory and Empirical Work,” The J. of Finance, Vol.25, No.2, pp. 383-417, 1970.

[4] [4] K. Schierholt and C. H. Dagli, “Stock market prediction using different neural network classification architectures,” IEEE/IAFE Conf. on Computational Intelligence for Financial Engineering, pp. 72-78, 1996.

[5] [5] P. K. H. Phua, Z. Xiaotian, and H. K. Chung, “Forecasting stock index increments using neural networks with trust region methods,” Int. Joint Conf. on Neural Networks, Vol.1, pp. 260-265, 2003.

[6] [6] P. D. Yoo, M. H, Kim, and T. Jan, “Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation,” Int. Conf. on Computational Intelligence for Modelling, Control and Automation and Intelligent Agents, Web Technologies and Internet Commerce, Vol.2, pp. 835-841, 2005.

[7] [7] C. Lu, “Integrating independent component analysis-based denoising scheme with neural network for stock price prediction,” Expert Systems with Applications Vol.37, pp. 7056-7064, 2010.

[8] [8] H. Li, C. H. Dagli, and D. Enke, “Forecasting Series-based Stock Price Data Using Direct Reinforcement Learning,” Int. Joint Conf. on Neural Networks, Vol.2, pp. 1103-1108, 2004.

[9] [9] T. Matsui and H. Ohwada, “A Reinforcement Learning Agent for Stock Trading: An Evaluation,” The 20th Annual Conf. of the Japanese Society for Artificial Intelligence, Vol.20, pp. 3C1-6, 2006.

[10] [10] M. Matsumoto, K. Fukui, K. Moriyama, S. Kurihara, and M. Numao, “A Design and Evaluation of Q-learning Agents on U-Mart,” The 20th Annual Conf. of the Japanese Society for Artificial Intelligence, 2006.

[11] [11] H. Li, C. H. Dagli, and D. Enke, “Short-term Stock Market Timing Prediction under Reinforcement Learning Schemes,” IEEE Int. Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 233-240, 2007.

[12] [12] J.W. Lee, “Stock Price Prediction Using Reinforcement Learning,” IEEE Int. Symposium on Industrial Electronics, Vol.1, pp. 690-695, 2001.

[13] [13] A. Sudo, A. Sato, and O. Hasegawa, “Associative Memory for Online Incremental Learning in Noisy Environments,” Int. Joint Conf. on Neural Networks, Vol.12, No.17, pp. 619-624, 2007.

[14] [14] S. Okada and O. Hasegawa, “Incremental Learning, Recognition, and Generation of Time-Series Patterns Based on Self-Organizing Segmentation,” J. of Advanced Computational Intelligence and Intelligent Informatics,Vol.10, No.3, pp. 395-408, 2006.