The linear exponential smoothing method, sometimes referred to as Holt's two-parameter model is a well-liked smoothing technique for trend-driven data forecasting. To get a final forecast, Holt's approach combines three independent equations.
Either minimizing the sum of the absolute one-step-ahead forecast errors or the sum of the squared one-step-ahead forecast errors can be used to select the smoothing parameters in an exponential smoothing algorithm. This article compares these two alternatives using the resulting forecast accuracy.
Recent history is given greater weight than ancient history in the exponential smoothing method. Level and trend are the two components that are modeled by double exponential smoothing, thus the name. The model adjusts when the known variables shift in level and trend.
To learn more about double exponential smoothing:
https://brainly.com/question/13181254
#SPJ4
