Forecasting Gold Price using Data Mining Techniques by Considering New Factors

Gold price forecast is of great importance. Many models have been presented by researchers to forecast gold price. It seems that although different models could forecast gold price under different conditions, the new factors affecting gold price forecast have a significant importance and effect on the increase in the forecast accuracy. In this work, different factors were studied in comparison with the previous studies on gold price forecast. In terms of time span, the collected data was divided into the three groups of daily, monthly, and annually. The conducted tests using new factors indicated an accuracy improvement of up to 2% in the neural networks methods, 7/3% in the time series method, and 5/6% in the linear regression method.