Abstract
This paper proposes a selective presentation learning technique for improving the learnability and predictability of large changes by back-propagation neural networks. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events into account. Training data corresponding to large changes of prediction-target time series are presented more often, and network learning is stopped at the point that has the maximal profit. When this technique is applied to daily stock-price prediction, the prediction error on large-change data was reduced by 11%, and the network's ability to make profits through experimental stock-trading was improved by 67% to 81%, in comparison with results obtained using conventional learning techniques.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Weigend A, Huberman B, Rumelhart D. Predicting the future: a connectionist approach. Int J Neural Systems 1990; 1(3): 193–209
Weigend A, Gershenfeld N. (eds). Time Series Prediction: Forecasting the Future and Understanding the Past. Addison-Wesley, Reading, MA, 1993
Chakraborty K, Mehrotra K, Mohan C, Ranka S. Forecasting the behavior of multivariate time series using neural networks. Neural Networks 1992; 5: 961–970
Vemuri V, Rogers R (eds). Artificial Neural Networks: Forecasting Time Series. IEEE Press, Los Alamitos, CA, 1994
White H. Economic prediction using neural networks: the case of IBM daily stock return. In: Proc Int Conf Neural Networks 1988; II-451–II-458. San Diego, CA
Kimoto T, Asakawa K, Yoda M, Takeoka M. Stock market prediction with modular neural networks. In: Proc Int Joint Conf Neural Networks 1990; I-1–I-6. San Diego, CA
Freisleben B. Stock market prediction with backpropagation networks. In: F Belli and J Rademacher (eds). Lecture Notes in Computer Science 604, pp. 451–460. Springer-Verlag, Heidelberg, 1992
Tan C. Trading a NYSE stock with a simple artificial neural network-based financial trading system. In: Proc New Zealand Int Two-Stream Conf Artificial Neural Networks and Expert Syst 1993; 294–295. Dunedin, New Zealand
Azoff E. Neural Network Time Series Forecasting of Financial Markets. John Wiley & Sons, West Sussex, 1994
Refenes A, Azema-Barac M. Neural network applications in financial asset management. Neural Comput & Applic 1994; 2(1): 13–39
Park D, El-Sharkawi M, Marks II R, Atlas L, Damborg M. Electric load forecasting using an artificial neural network. IEEE Trans Power Syst 1991; 6(2): 442–449
Caire P, Hatabian G, Muller C. Progress in forecasting by neural networks. In: Proc Int Joint Conf Neural Networks 1992; II-540–II-545. Baltimore, MD
Kohara K, Ishikawa T. Multivariate prediction using prior knowledge and neural heuristics. In: Proc Int Symposium on Integrating Knowledge and Neural Heuristics 1994; 179–188. Pensacola, FL
Giles C, Omlin C. Rule refinement with recurrent neural networks. In: Proc Int Conf Neural Networks 1993; 801–806. San Francisco, CA
Abu-Mostafa Y. A method for learning from hints. In: S Hansonet al. (eds) Advances in Neural Information Processing Systems, Vol. 5. Morgan Kaufmann, San Mateo, CA, 1993
Rumelhart D, Hinton G, Williams R. Learning internal representations by error propagation. In: D Rumelhart, J McClelland and the PDP Research Group (eds) Parallel Distributed Processing 1986; 1. MIT Press, Cambridge, MA
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kohara, K., Fukuhara, Y. & Nakamura, Y. Selective presentation learning for neural network forecasting of stock markets. Neural Comput & Applic 4, 143–148 (1996). https://doi.org/10.1007/BF01414874
Issue Date:
DOI: https://doi.org/10.1007/BF01414874