CASE # 6  ALTAVOX ELECTRONICS

Textbook: Operations and Supply Chain Management:  Robert Jacobs and Richard B. Chase

3 questions/2 pages

Altavox is a manufacturer and distributor of many electronic instruments and devices, including digital/analog multimeters, function generators, oscilloscopes, frequency counters and other test equipment and measuring equipment.  Altavox sells a line of test meters that are popular with professional electricians.  The model VC202 is sold through five distributors to retail stores in the United States.  These distributors are located in Atlanta, Boston, Chicago, Dallas and Los angles and have been selected to serve different region in the country.

The Model VC202 has been a steady seller over the years due to its reliability and rugged construction.  Altavox does not consider this a seasonal product, but there is some variability in demand.  Demand for the product over the past 13 weeks is shown in the following table.

These data are contained in an Excel spread Altavox Data.  The demand in the regions varies between high of 40 units on average per week in Atlanta and 48 units in Dallas.  This quarter’s data are pretty close to the demand last quarter.

Management would like you to experiment with some forecasting models to determine what should be used in a new system being implemented.  This new system is programmed to use one of two models: simple moving average or exponential smoothing.

Question 1

Consider using a simple moving average model.  Experiment with models using five week’s and three weeks’ past data.  The past data in each region is given below (week – 1 is the week before week 1 in the table, -2 is two weeks before week 1, etc.).  Evaluate the forecast that would have been made over the 13 weeks for each distributor using the mean absolute deviation, mean absolute percent error, and tracking signal as criteria.

Question 2

Next consider using a simple exponential smoothing model.  In your analysis, test two alpha values, .2 and .4.  Use the same criteria for evaluating the model as in question 1.  Assume that the initial previous forecast for the model using an alpha value of .2 is the past three-week average.  For the model using an alpha of .4 assume that the previous forecast is the past five-week average.

Question 3

Altavox is considering a new option for distributing the model VC202 where, instead of using five distributors, only a single distributor would be used.  Evaluate this option by analyzing how accurate the forecast would be based on the demand aggregated across all regions.  Use the model that you think is best from your analysis of questions 1 and 2.  What are the advantages and disadvantages of aggregating demand from a forecasting view?  Are there other things that should be considered when going from multiple distributors to a single distributor?