A Job-shop manufacturer that specializes in replacement parts has no forecasting system in place and manufactures products based on last month's sales. 24 months of data are available as given in the following Table.
Month ____________________Sales
Jan-05................................430
Feb...................................420
Mar..................................436
Apr..................................452
May.................................477
Jun..................................420
Jul...................................398
Aug.................................501
Sep.................................514
Oct.................................532
Nov.................................512
Dec.................................410
Jan-06..............................442
Feb..................................449
Mar.................................458
Apr.................................472
May.................................463
Jun...................................431
Jul...................................400
Aug.................................487
Sep..................................503
Oct..................................503
Nov.................................548
Dec..................................432
Plot the data using Excel. What kind of pattern do you observe?
Use a naive model to generate monthly sales forecasts (e.g. the February 2005 forecast is given by the January 2005 value, and so forth). Compute the MAPE and MSE. (Use Excel.)
Use simple exponential smoothing with smoothing constants 0.1 and 0.6. What are the MAPE and MSE values? (Use Minitab).
Calculate the autocorrelations for the residuals of the methods used in part c. What do you observe?
Use Winter's method with smoothing constants α = β = γ = 0.5. Calculate the autocorrelations for the residuals. Compare the MSE and MAPE of this method with the previous ones.
What are your comments regarding the best method to use in forecasting the above data set? Explain.