Question

A can opener manufacturer has had monthly sales for a seven-month period as follows:

Month	Sales (000 units)
Feb.	19
Mar.	18
Apr.	15
May	20
Jun.	18
Jul.	22
Aug.	20

a) Plot the data

b) Forecast September's sales volume and the previous months and calculate MAD for each method using each of the following:

1)The naïve approach.

2)A four-month moving average.

3)A weighted average using .50 for the recent month, .30 for 2 months ago, and .20 for 3 months ago.

4)Which method seems most appropriate? Why?

Answer 1

Answer a: data plotted in image

Answer b: Calculations are given in attached figure

Absolute deviation= |Forecast - Sales|

MAD= mean absolute deviation= sum of absolute deviation/no. of months

1) In Naïve forecast we take the sales of previous months and make it the forecast of next month.

2) Forecast of a month with four period moving average = (sales of most recent month+ sales of next most recent month+ sales of third recent month+ sales of fourth recent month)/4

3) Weighted forecast of a month = 0.5*(sales of most recent month) +0.3*(sales of next most recent month) +0.2(sales of third recent month)

4) Four period moving average seemed most appropriate because it has the least value of Mean absolute deviation (MAD). MAD represents the mean of errors in forecast, so less the MAD better is forecast.