Abstract

It is well known that short-term market price prediction has been a difficult problem for a long time because of too many factors which cannot be accurately predicted. Usually time series analysis has been often employed in modeling short-term price predictions. In recent years a new technique of artificial neural networks ANN has been proposed as an efficient tool for modeling and forecasting. A feed-forward ANN model has been developed for short-term price forecasting of stocks and in comparison with time series model ARIMA in this study. The data used include daily price, weekly price (average) and monthly price (average). The results showed that ANN model clearly outperformed the time series model in forecasting the cost before one day or one week. A fine relationship between the modeled and the real prices observed from the feed-forward ANN model, with a relative error less than 5.0%.Index.

Authors and Affiliations