Session

Computer Science and Information Systems

Description

The aim of this paper is to design a neural network model trained with genetic algorithms, called 'neuro-genetic' model, and to use it in Gross Domestic Product (GDP) forecasting. GDP is an economic indicator that represents the value at market prices of all goods and services produced within a country in a given period (usually a year). Its forecasting is of particular importance for the fiscal and monetary policy makers in the preparation of timetables aiming macroeconomic stability and su stainable economic growth. We use ten factors that affect the determination of the GDP for the Albania’s GDP forecasting. The genetic algorithm is used to train the weights of different architecture MLPs. We compare the output of these neural networks (NN) and find the best NN architecture which archives the high accuracy for GDP forecasting.

Keywords:

artificial neural networks, genetic algorithm, forecasting, GDP

Session Chair

Peter Kopacek

Session Co-Chair

Selman Haxhijaha

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-437-24-0

First Page

58

Last Page

64

Location

Durres, Albania

Start Date

2-11-2013 9:45 AM

End Date

2-11-2013 10:00 AM

Share

COinS
 
Nov 2nd, 9:45 AM Nov 2nd, 10:00 AM

A Neuro-Genetic Model in GDP Forecasting: Case Study Albania

Durres, Albania

The aim of this paper is to design a neural network model trained with genetic algorithms, called 'neuro-genetic' model, and to use it in Gross Domestic Product (GDP) forecasting. GDP is an economic indicator that represents the value at market prices of all goods and services produced within a country in a given period (usually a year). Its forecasting is of particular importance for the fiscal and monetary policy makers in the preparation of timetables aiming macroeconomic stability and su stainable economic growth. We use ten factors that affect the determination of the GDP for the Albania’s GDP forecasting. The genetic algorithm is used to train the weights of different architecture MLPs. We compare the output of these neural networks (NN) and find the best NN architecture which archives the high accuracy for GDP forecasting.