Evolutionarily Developed Neural Networks for Investment Strategies Construction
The study presents the idea of feedforward evolutionary neural network that utilizes (instead of classical training) a specific evolutionary procedure for network development. This procedure is responsible for network evolving, connections selection and weight values determination. Basic features of such networks and the algorithm of network development are submitted. Such a network has been applied to a problem of construction of investment strategy for Polish stock index WIG 20. The evolutionary network development process has been characterized and discussed. Relatively good results of application of generated by the network investment strategies have been obtained for the test data.
KeywordsBasic Layer Return Rate Investment Strategy Network Development Bayesian Neural Network
Unable to display preview. Download preview PDF.
- 1.Bauer R. (1994) Genetic Algorithms and Investment Strategies. Wiley, New YorkGoogle Scholar
- 2.Morajda J. (1999) Applications of Neural Networks in the Financial Markets - Selected Aspects. Proc. of the 4th Conf. “Neural Networks and Their Applications”, ZakopaneGoogle Scholar
- 3.Refenes A. P. (1995) Neural Networks in the Capital Markets. Wiley, ChichesterGoogle Scholar
- 4.Rutkowska D., Pilinski M., Rutkowski L. (1997) Neural Networks, Genetic Algorithms and Fuzzy Systems. PWN Warszawa-Lódz (in Polish)Google Scholar
- 5.Tadeusiewicz R. (1993) Neural Networks. AOW RM Warszawa (in Polish)Google Scholar
- 6.Yao X. (1995) Evolutionary Artificial Neural Networks. Encyclopedia of Computer Science and Technology, Marcel Dekker Inc., New York.Google Scholar