Simple Moving Average Method

In this method, only the most recent data is relevant for estimating future demand. For the m-month moving average method (m n), only the average of the past m months data is used  

Using the 3-month moving average method for the example data given in Table 2.1, we get 

Note that all the demands used in the moving average method are given 

---

To develop the tool, we have considered only simple forecasting methods, such as moving averages and exponential smoothing, so that each level of the chain uses the best one that suits the demand it should deal with. With them, it is possible to achieve great results in reducing Bullwhip Effect. Even so, we have also shown that the inclusion of more advanced forecasting methods (ARIMA models) allows an even better system performance. 

The moving average is a simple times-series method. It is just the average of the demand for a set of the most recent periods. For example, if demand for the last 4 weeks was 100,120,130, and 120 for weeks 1 to 4, respectively, and if the number of periods to be averaged is n, then n = 4 and the moving average is calculated as ... 

Estimate demand for the next 4 weeks using a 4-week moving average as well as simple exponential smoothing with a = 0.1. Evaluate the MAD, MAPE, MSE, bias, and TS in each case. Which of the two methods do you prefer Why ... 

Consider monthly demand for the ABC Coiporation as shown in Table 7-3. Forecast the monthly demand for Year 6 using moving average, simple exponential smoothing, Holt s model, and Winter s model. In each case, evaluate the bias, TS, MAD, MAPE, and MSE. Which forecasting method do you prefer Why ... 

Both simple methods and more complex methods have been presented in this article. While there are certain concerns and weaknesses for the simple methods such as lack of independence, those methods have proved adequate for many production operations over the years and those simple methods are recommended as an initial effort. The use of more sophisticated methods, even including moving average and CUSUM control charts, as well as DOE and the highly complex methods suggested for autocorrelated data, such as that found in nuclear and process industries, is based on a matter of need and level of technical understanding of what is to be accomplished. 

Crowder, S., A Simple Method for Studying Run Length Distributions of Exponentially Weighted Moving Average Charts, Technometrics, 29, 401-407 (1987). 

A simple calculation method, which takes into account the fountain effect, was proposed.289 In this approach the flow is assumed to be laminar and unidimensional. The front of the stream is regarded as straight (plane), perpendicular to the walls of the mold and moving with a constant average velocity vav. Then the following dimensionless variables are introduced ... 

---