Application of artificial neural networks to stock price prediction

• Autorzy: Witkowska, D.
• Języki publikacji: EN

Abstrakty

EN

Artificial neural networks are non-linear models that can be trained to extract hidden structures and relationships that govern the data. They can be used for analyzing relations among economic and financial phenomena. In the paper we discuss our research on application of three forecasting methods. These methods are: econometric model, AR(3) and the back propagation algorithm. The prediction of share prices of three companies listed on the Warsaw Stock Exchange was made. The accuracy of forecasting was evaluated in terms of percentage errors MAPE and RASE.

Słowa kluczowe

PL

cena hurtowa; predykcja; model ekonometryczny; sztuczna sieć neuronowa

EN

stock prices; prediction; econometric models; artificial neural network

• Czasopismo: Journal of Applied Computer Science
• Rocznik: 1999
• Tom: Vol. 7, nr 1
• Strony: 79-89
• Opis fizyczny: Bibliogr. 13 poz.

Twórcy

autor

Witkowska, D.

• Institute of Management