بررسي عوامل موثر بر قيمت طلا و ارايه مدل پيش بيني قيمت آن به كمك شبكه هاي عصبي فازي

Throughout the history man has considered gold as a precious metal and its forcast has always been important. Traditional methods of forcast, e.g.Regresion, ARIMA, Exponential Smoothing, Moving Average, and methods of this kind have been applied. Only recently Artificial Intelligence, Neural Networks and Fuzzy Logic have been proposed as forcast models. In this paper after considering gold role in the international finance, its Demand and supply, and the relationship between gold and Dollar, factors affecting the gold price fluctuations are considered; then a Neuro-Fuzzy approach based on the Takagy-Sogno Moel is employed to forcast gold price. The results obtained by this method are compared with Regression Analysis, which show that a Neuro-Fuzzy yields a better and more promissing forcast.