Single Exponential Smoothing (ema) does not excel in following the data when there is a trend. This situation can be improved by the introduction of a second equation with a second constant gamma.
The gamma constant cant be lower than 0 and cant be greater than 1, higher values of gamma create less lag while preserving smoothness.Higher values of length must be followed by higher values of gamma in order to keep the lag low.
The first smoothing part consist of a classic ema but we add s-s1 to the previous smoothed value, this will help decrease lag.The second smoothing part then updates the trend, which is expressed as the difference between the last two values.
릴리즈 노트
⋅
Single Exponential Smoothing (ema) does not excel in following the data when there is a trend. This situation can be improved by the introduction of a second equation with a second constant gamma.
Like alpha, the gamma constant cant be lower than 0 and cant be greater than 1, higher values of gamma create less lag while preserving smoothness.Lower values of alpha must be followed by higher values of gamma in order to keep the lag low.
The first smoothing part consist of a classic ema but we add s-s1 to the previous smoothed value, this will help decrease lag.The second smoothing part then updates the trend, which is expressed as the difference between the last two values.