The influence of using fractal analysis in hybrid MLP model for short-term forecast of closing prices on Warsaw Stock Exchange
Michał Paluch, Lidia Jackowska-Strumiłło
DOI: http://dx.doi.org/10.15439/2014F358
Citation: Proceedings of the 2014 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 2, pages 111–118 (2014)
Abstract. The paper describes a new method of combining Artificial Neural Networks (ANN), technical analysis and fractal analysis for predicting share prices on the Warsaw Stock Exchange. The proposed hybrid model consists of two consecutive modules. In the first step share prices are pre-processed and calculated into moving averages and oscillators. Then, in the next step, they are given to the ANN inputs, which provides the closing values of the asset for the next day. ANN of Multi-Layer Perceptron (MLP) type, and fractal analysis are applied. The hybrid model combining ANN with technical and fractal analysis is compared with hybrid model combining ANN with technical analysis. The obtained results indicate that hybrid model combined with fractal analysis is more accurate and stable in the long run than the hybrid model.