The model uses a stationary econometrics model to forecast
gold prices. The stationary stochastic process denotes that the
mean and variance of a variable are constant over the time.
Moreover, covariance in the two different periods depends on gap
or lag between the periods, not actual time at which the
covariance is computed. For example, if the gold price time series
is stationary, the mean, variance and autocovariance in various
lags remain the same irrespective at what point they are
measured. Therefore, some of the time series will tend to be its
mean or median and fluctuate around it with constant amplitude
called mean reversion