Exponential smoothing is actually a special type of weighted moving average method. Its characteristics are: First, exponential smoothing further strengthens the role of recent observations in the forecast by assigning unequal weights to observations at different times, thus increasing the weights of recent observations so that the forecast can quickly reflect actual market changes. The weights are reduced in equal steps, and the first term of this step is the smoothing constant a, with the common ratio (1- a). Second, the exponential smoothing method is scalable for the weights assigned to the observations, and different values of a can be taken to change the rate of change of the weights. If a is taken as a small value, the weights change more rapidly and the recent trend of the observed values is reflected more rapidly in the exponential moving average. Thus, using exponential smoothing, different values of a can be chosen to adjust the degree of homogeneity (i.e., the smoothness of the trend change) of the time series observations.