Combining Selective-Presentation and Selective-Learning-Rate Approaches for Neural Network Forecasting of Stock Markets

Kazuhiro Kohara

2008

Abstract

We have investigated selective learning techniques for improving the ability of back-propagation neural networks to predict large changes. We previously proposed the selective-presentation approach, in which the training data corresponding to large changes in the prediction-target time series are presented more often, and selective-learning-rate approach, in which the learning rate for training data corresponding to small changes is reduced. This paper proposes combining these two approaches to achieve fine-tuned and step-by-step selective learning of neural networks according to the degree of change. Daily stock prices are predicted as a noisy real-world problem. Combining these two approaches further improved the performance.

References

  1. Weigend, A., Huberman, B., Rumelhart, D.: Predicting the future: a connectionist approach. International Journal of Neural Systems, Vol. 1, No. 3. (1990) 193-209
  2. Vemuri, V., Rogers, R. (eds): Artificial Neural Networks: Forecasting Time Series. IEEE Press, Los Alamitos, CA (1994)
  3. Pham, D., Liu, X.: Neural Networks for Identification, Prediction and Control. Springer (1995)
  4. Kil, D., Shin, F.: Pattern Recognition and Prediction with Applications to Signal Characterization. American Institute of Physics Press (1996)
  5. Mandic, D., Chambers, J.: Recurrent Neural Networks for Prediction. John Wiley & Sons (2001)
  6. Azoff, E.: Neural Network Time Series Forecasting of Financial Markets. John Wiley and Sons, West Sussex (1994)
  7. Refenes, A., Azema-Barac, M.: Neural network applications in financial asset management. Neural Computing & Applications, Vol. 2, No. 1. Springer-Verlag, London (1994) 13-39
  8. White, H.: Economic prediction using neural networks: the case of IBM daily stock return. Proceedings of International Conference on Neural Networks. San Diego, CA (1988) II451-II-458
  9. Baba, N., Kozaki, M.: An intelligent forecasting system of stock price using neural networks. Proceedings of International Conference on Neural Networks. Singapore (1992) I371-I-377
  10. Freisleben, B.: Stock market prediction with backpropagation networks. Lecture Notes in Computer Science, Vol. 604. Springer-Verlag, Heidelberg (1992) 451-460
  11. Tang, Z., Almeida, C., Fishwick, P.: Time series forecasting using neural networks vs. BoxJenkins methodology. Simulation, Vol. 57, No. 5. (1991) 303-310
  12. Kohara, K., Fukuhara, Y., Nakamura, Y.: Selective presentation learning for neural network forecasting of stock markets. Neural Computing & Applications, Vol. 4, No. 3. SpringerVerlag, London (1996) 143-148
  13. Kohara, K., Fukuhara, Y., Nakamura, Y.: Selectively intensive learning to improve largechange prediction by neural networks. Proceedings of International Conference on Engineering Applications of Neural Networks. London (1996) 463-466
  14. Kohara, K.: Selective-learning-rate approach for stock market prediction by simple recurrent neural networks. Lecture Notes in Artificial Intelligence, Vol. 2773. Springer-Verlag, Heidelberg, (2003) 141-147
  15. Kohara, K.: Neural networks for economic forecasting problems. In: Cornelius T. Leondes (ed): Expert Systems -The Technology of Knowledge Management and Decision Making for the 21st Century-. Academic Press. San Diego, CA (2002)
  16. Kohara, K.: Foreign Exchange Rate Prediction with Selective Learning BPNNs and SOMs. Proceedings of World Multi-Conference on Systemics, Cybernetics and Informatics. Orland, FL (2005) 350-354
  17. Park, D., El-Sharkawi, M., Marks II, R., Atlas, L., Damborg, M.: Electric load forecasting using an artificial neural network. IEEE Transactions on Power Systems. Vol. 6, No. 2. (1991) 442-449
Download


Paper Citation


in Harvard Style

Kohara K. (2008). Combining Selective-Presentation and Selective-Learning-Rate Approaches for Neural Network Forecasting of Stock Markets . In Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008) ISBN 978-989-8111-33-3, pages 3-9. DOI: 10.5220/0001508200030009


in Bibtex Style

@conference{anniip08,
author={Kazuhiro Kohara},
title={Combining Selective-Presentation and Selective-Learning-Rate Approaches for Neural Network Forecasting of Stock Markets},
booktitle={Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)},
year={2008},
pages={3-9},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001508200030009},
isbn={978-989-8111-33-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2008)
TI - Combining Selective-Presentation and Selective-Learning-Rate Approaches for Neural Network Forecasting of Stock Markets
SN - 978-989-8111-33-3
AU - Kohara K.
PY - 2008
SP - 3
EP - 9
DO - 10.5220/0001508200030009