[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Archive :: Search :: Submit :: Contact ::
Main Menu
Home::
Journal Information::
Articles archive::
For Authors::
For Reviewers::
Registration::
Contact us::
Site Facilities::
Webmail::
::
Search in website

Advanced Search
..
Receive site information
Enter your Email in the following box to receive the site news and information.
..
:: Search published articles ::
Showing 6 results for Neural Network

Dr Mohamad Ali Motafakkerazad, Aidin Ghafarnejad Mehraban, ,
Volume 1, Issue 4 (9-2011)
Abstract

Monetary shocks are one of the control tools in economic systems. A true perception of these shocks on economic systems can lead us to a suitable policy. In this paper, the impact of monetary shocks on output in Iran has been modeled and investigated using artificial neural networks. We investigated positive and negative shocks separately and confirmed asymmetric effect of these shocks. In addition, nonlinear natures of output changes considering magnitude of shocks were obtained. Results show that optimal condition of monetary shocks to gain maximum output growth can be reached using artificial neural network. In other words, symmetric or asymmetric behavior of monetary shocks depends on economic situation in considered year or period. In addition to, investigation of monetary shocks effect (positive or negative impact) on the production changes, depending on the shock value and this shocks do not have an only particular Effect on production changes. Its can be different.
Esmaeil Naderi, Dr Hossein Abbasi-Nejad,
Volume 2, Issue 8 (9-2012)
Abstract

This study investigates predictability, chaos analysis, wavelet decomposition and the performance of neural network models in forecasting the return series of the Tehran Stock Exchange Index (TEDPIX). For this purpose, the daily data from April 24, 2009 to May 3, 2012 is used. Results show that TEDPIX series is chaotic and predictable with nonlinear effect. Also, according to obtained inverse of the largest lyapunov exponent, we are able to predict the future values of the series up to 31 days. Besides, our findings suggest that multi-layer feed forward neural network model and fuzzy model based on decomposed data, are of superior performances in predicting the return series. It is worth mentioning that, among these models, MFNN reveals the best performance.


Mohammad Najar Firouz Jayi, Bahare Oryani, Mahdi Zolfaqari,
Volume 4, Issue 14 (3-2014)
Abstract

This report investigates the dominant factors influencing the price gap and the symmetry principle’s evaluation between the crude oil’s price and gasoline. In this regard, the Brent’s crude oil price, gasoline price in six European countries and the fluctuations of the euro vs. US dollar’s exchange rate over the period of 1/1/1999 to 8/25/2011 in weekly intervals are studied. For this purpose, linear models and nonlinear models, such as artificial neural network and wavelet transformation, are implemented. The results indicate insignificant impact of the mentioned parameters in short period price gap both for linear and nonlinear simulations, but nonlinear modeling explicates 92% of long period fluctuations in price gap. According to linear/nonlinear models the symmetry principle is accepted for short period fluctuations in crude oil’s price, but not for long periods.
Keyvan Shahab Lavasani, Hossein Abbasi Nejad,
Volume 5, Issue 18 (3-2015)
Abstract

Generally,some booms in housing prices are followed by busts. One common phenomenon relating these changes is that the house price cycle is generally believed to the product of the short-run deviations from the long-run upward trends. The long-term cyclical fluctuation in Iran’s housing market was periodically occurred about every 6 years.
 Furthermore, Movements in house prices have significant impact on household welfare, financial stability and business cycles. Being able to forecast housing price booms is therefore of central importance for central banks, financial supervision authorities as well as for other economic agents. However, forecasting house prices using only a single or a few selected variables at a time intuitively appears efficient because only a single variable almost contain all of the pertinent investigative information about the past behavior of the variable. In this study, wavelet decomposition has been used to extract the cyclical components of house price, and then using the cyclical components and neural network methodwe start to forecast the booms in housing prices in 2013.
Elham Gholami, Yegane Mousavi Jahromi,
Volume 5, Issue 20 (9-2015)
Abstract

Cigarette and tobacco products in the VAT Law is considered as one of the particular goods and in order to contorlingit’s consumption by price tools, higher tax rates than the standard rate will be levied on it. In this paper, forecasting of revenues of this tax using an approach based on the estimating of tax base has been considered. Thus the first stage, tax base (consumption expenditure) is forecasted for the period 2012 to 2015 and then tax related years by applying the tax rates, will be calculated. In this regard, Because of concerns that policy makers have access to accurate predictions of tax revenues, Supervised neural networks Method to prediction and back-propagation algorithm to train is used. The results indicate that the average annual growth of revenue from value added tax on Cigarette consumption will have 20 percent during the forecasting years.
Seyed Kamal Sadeghi, Seyed Mehdi Mousavian,
Volume 5, Issue 20 (9-2015)
Abstract

As one of the important energy forms, natural gas consumption has an upward trend in recent years. Therefore management and planning for provision of it requires prediction of the future consumption. But many of prediction procedures are inherently stochastic therefore it is important to have better knowledge about the robustness of prediction procedures. This paper compares robustness of two prediction procedures Artificial Neural Networks as a nonlinear and ARIMA as a linear model. using resampling method to predict the monthly consumption of natural gas in the household sector. Data spans from 2001-4 to 2012-3, to train the networks, we used genetic algorithms and Particle Swarming Optimization then results were compared using 10-fold method. According to the results, the particle swarm optimization (PSO) outperforms the genetic algorithm. Then we used data from 2001-4 to 2010-3, with resampling by 2000 to predict the  natural gas consumption for the 2001 -4 to 2012-3 and to form critical values. Results show that prediction by a mixed method using ANN and PSO is more robust than ARIMA method.



Page 1 from 1     

فصلنامه تحقیقات مدلسازی اقتصادی Journal of Economic Modeling Research
Persian site map - English site map - Created in 0.07 seconds with 30 queries by YEKTAWEB 4666