I'd like to use Simple Exponential smoothing to forecast the lead-time demand for inventory control, I have monthly data and LT+1 is equal to 5 months, can I do a forecast using SES which gives me a one-period-ahead forecast and then multiply it by 5 to get the forecast for LT+1 ? what is the best solution to get h step ahead forecast(like LT+1)when the forecast method is SES? Thank you
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Yes, for Single Exponential Smoothing, the lead time demand (which is the sum of the forecasts over the lead time) is necessarily a simple multiple of a one-step-forecast.
If you use a more complex model (with seasonality and/or trend), this will of course not hold any more. In addition, you will need to think about safety stocks and quantile forecasts.
I recommend this free online textbook on forecasting.
answered Nov 28, 2012 at 14:04