استفاده از مدل شبکه عصبی مصنوعی در پیش بینی شاخص بازار سهام

Forecasting stock exchange rates is an important financial problem that is receiving increasing attention. During the last few years, a number of neural network models and hybrid models have been proposed for obtaining accurate prediction results, in an attempt to outperform the traditional linear and nonlinear approaches. This paper evaluates the effectiveness of neural network models which are known to be dynamic and effective in stock-market predictions. The models analysed are multi-layer perceptron (MLP), dynamic artificial neural network (DAN2) and the hybrid neural networks which use generalized autoregressive conditional heteroscedasticity (GARCH) to extract new input variables. The comparison for each model is done in two view points: Mean Square Error (MSE) and Mean Absolute Deviate (MAD) using real exchange daily rate values of NASDAQ Stock Exchange index.

Forecasting simply means understanding which variables lead to predict other variables (Mcnelis, 2005). This means a clear understanding of the timing of lead-lag relations among many variables, understanding the statistical significance of these lead-lag relations and learning which variables are the more important ones to watch as signals for predicting the market moves. Better forecasting is the key element for better financial decision making, in the increasing financial market volatility and internationalized capital flows. Accurate forecasting methods are crucial for portfolio management by commercial and investment banks. Assessing expected returns relative to risk presumes that portfolio strategists understand the distribution of returns. Financial expert can easily model the influence of tangible assets to the market value, but not intangible asset like know-how and trademark. The financial time series models expressed by financial theories have been the basis for forecasting a series of data in the twentieth century. Studies focusing on forecasting the stock markets have been mostly preoccupied with forecasting volatilites. There has been few studies bringing models from other forecasting areas such as technology forecasting. To model the market value, one of the best ways is the use of expert systems with artificial neural networks (ANN), which do not contain standard formulas and can easily adapt the changes of the market. In literature many artificial neural network models are evaluated against statistical models for forecasting the market value. It is observed that in most of the cases ANN models give better result than other methods. However, there are very few studies comparing the ANN models do among themselves, where this study is filling a gap. Objective of this study is to compare performance of most recent ANN models in forecasting time series used in market values. Autoregressive Conditional Heteroscedasticity (ARCH) model (Engle, 1982), generalized version of ARCH model Generalized ARCH (GARCH) model (Bollerslev, 1986), Exponential GARCH (EGARCH) model (Nelson, 1991) and Dynamic Architecture for Artificial Neural Networks (DAN2). Ghiassi and Saidane (2005) will be analyzed in comparison to classical Multi-Layer Perceptron (MLP) model. Despite the popularity and implementation of the ANN models in many complex financial markets directly, shortcomings are observed. The noise that caused by changes in market conditions, it is hard to reflect the market variables directly into the models without any assumptions (Roh, 2007). That is why the new models will also be executed in hybrid combination with MLP. The analysed models will be tested on NASDAQ index data for nine months and the methods will be compared by using Mean Square Error (MSE) and Mean Absolute Deviation (MAD). The remaining sections of this paper are organized as follows: Section 2 gives the background of the related studies; Section 3 introduces the models used in this study and Section 4 provides results of each model using daily exchange rates of NASDAQ index. Final section gives the conclusion and recommendations for future researches. This study will not only make contribution to the ANN research but also to the business implementations of market value calculation.

This study is in search for reducing the shortcomings of using ANN in predicting the market values. With this aim this study motivated from a new ANN model; DAN2 developed by Ghiassi & Saidane (2005) and the hybrid models (GARCH-ANN, EGARCH-ANN) developed by Roh (2007). In order to present the differences in accuracy of prediction, all the models are applied on the same set of data retrieved from NASDAQ Stock exchange. The results show that classical ANN model MLP outperforms DAN2 and GARCH-MLP with a little difference. GARCH inputs had a noise effect on DAN2 because of the inconsistencies explained in the previous section and GARCH-DAN2 clearly had the worst results. Thus further researches’ should focus on improving DAN2 architecture. At least for now, simple MLP seems to be the best and practical ANN architecture. When the MLP model used to forecast the future movements of the NASDAQ index, MLP model correctly forecasted the first movement as down. The realized value (1747.17) had very small difference (0.54%) with the forecasted value (1737.70). Thus MLP is a powerful and practical tool for forecasting stock movements. Since hybrid models (GARCH-ANN) do not give satisfying results, despite Roh’s (2007) research, a lot of time series should be used to understand the inner dynamics of hybrid models, before making a conclusion about hybrid models performance. Roh reported that 20–25 % of the learning of each ANN came from GARCH or E-GARCH input variables, which are inputs of technical analysis, but 75–80 % in that research many other correlated variables, which are inputs of fundamental analysis, such as bond yields, bond prices, contract volume etc. Further researches should be focus to discover whether GARCH, E-GARCH has a correcting effect on forecasts or other correlated variables has a corrective effect on forecasts. The results of these further researches will lead us to many powerful financial time series forecasting models.