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
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.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