Forecasting gold prices using holt's exponential smoothing method

Forecasting is an important part of decision making and many of our decisions are based on estimation of future unknown events. In a more general term it is commonly known as prediction which refers to estimation of time series or longitudinal type data. Gold is a precious yellow commodity once used as a money. It was made illegal in USA 41 years ago, but is now once again accepted as a potential currency. The demand for this commodity is on the rise. Objective of this study was to develop a forecasting model for predicting gold prices based on economic factors such as inflation currency price movements. Due to the increase in demand for gold, it is necessary to develop a model that reflects the structure and pattern of gold market and forecast movements of gold prices. In this present study it is suggested that for forecasting the gold prices, the optimum technique is the Holt's exponential smoothing model. For getting this conclusion we have collected the data on average monthly gold prices for period of 7 years from Jan2008 to Dec2014 obtained from World Gold Council and applied Single Exponential Smoothing Method, Holt's Exponential Smoothing Method and Auto Regressive Moving Average (ARMA) Methods. By comparing the above techniques using MAPE measure, it was found that MAPE is minimum for Holt's method. Using this method to forecast the gold prices for the succeeding period.