Paper Information

Journal:   TAHGHIGHAT-E-EGHTESADI   Fall-Winter 2003-2004 , Volume _ , Number 63; Page(s) 4 To 4.
 
Paper: 

FORECASTING METHODS EVALUATION OF STOCK PRICES AND PROPOSING A NONLINEAR MODEL USING NEURAL NETWORKS

 
 
Author(s):  KHALOUZADEH H., KHAKI SEDIGH A.
 
* 
 
Abstract: 
In this paper, we deal with several time series of share prices and daily returns of different companies which are members of the Tehran Stock Exchange. Three prediction methods are used for time series forecasting. The first method, is based on the linear models (ARIMA) for short term and long term forecasting. The second method, is based on the nonlinear neural nenvorks model and the third method is a neural networks model with a special structure. It has been shown the time series generator process of these companies are complex nonlinear mappings and the methods based on the various linear modelling strategies are unable to identify these dynamics. Also, it has been shown by using the conventional structure of the nonlinear neural networks that one can not obtain a satisfactory results for long term forecasting. Finally, it is shown that the proposed structrure, provides accurate next step and the long term share prices and daily returns forecasting.
 
Keyword(s): LINEAR MODELS, TIME SERIES FORECASTING, MODELING, FORECASTABILITY, NONLINEAR TIME SERIES ANALYSIS, CHAOTIC PROCESSES, ARTIFICIAL NEURAL NETWORKS.
 
References: 
  • ندارد
 
  Yearly Visit 67
 
Latest on Blog
Enter SID Blog