پيش بيني قيمت طلا با بكارگيري مدل تركيبي مدل هاي خود رگرسيون ميانگين متحرك انباشته كلاسيك با منطق فازي

Gold Price Forecasting Using a Hybrid Auto-Regressive Integrated Moving Average Models and Fuzzy Logic

Priceless metals such as gold. silver and platinum are one of the most effective variables on financial systems and forecasting them is very important for economic decision makers. Rapid changes of under-study systems in real world and specifically in financial markets have created problems for forecasters in order to collect the necessary data. Quantitative forecasting models such as Auto-Regressive Integrated Moving Average (ARlMA) models and Artificial Neural Networks (ANNs) need a large amount of historical data in order to yield accurate results. Fuzzy forecasting models such as fuzzy regression are suitable models in less-data situations; however, their performance is not always satisfactory. Using hybrid models or combining several models has become a common practice in order to overcome the limitations of the single models and improve the forecasting accuracy. In this paper, a hybrid ARlMA and fuzzy logic model (FARlMA) is proposed in order to overcome the data limitation of ARIMA models and obtain more accurate result. Empirical results of gold price forecasting indicate that the proposed model can be an effective way to predict the interval changes of gold price.