2.1.1 Forecasting Models [7]
Moving Average: The moving average is moving because we look each time at the last N values. All these
values have the same importance.
Exponential Smoothing: All the past data give decreasing weights. The curves correspond to the forecasts
obtained using the exponential smoothing method with a factor
Linear Regression: The regression analysis aims at fitting a straight line in the set of points. Since there are
different ways of fitting the curve, an objective must be selected.
Double Exponential Smoothing: By using an exponential smoothing, decreasing weights will be given to the
data. The goal here is also to determine the model parameters and .
Winters' Method: The method here consists in a triple exponential smoothing by which all the model
parameters are updated when a new observation is obtained.
CMA Method: Two different methods will be described. The first method is CMA stands for centered moving
average. The second method is called triple exponential smoothing or method of Winters.
Seasonal times series: The CMA values can thus be seen as rough estimates of the real demand without
seasonal variation.