section 4
30 The number of eases of me
SUPPLY AND Deano PLAssiNG
lot wine sold by the Connor Owen winery in an eight-year period
is as follows:
Yea Casts oF MetLor Wine Year Casts or Mentor Wie
2002 270 2006 358
2003 36 2007 00
2004 ve 2008 40
2005 456 2009 6
Using an exponential smoothing model with an alpha value of 0.20, estimate the smoothed
value calculated as of the end of 2009. Use the average demand for 2002 through 2008 as your
inital forecast then smooth the forecast forwatd to 2009.
CASE: Atravox EvectRONics
Altavox is a manufacturer and distributor of many different elec
tronic instruments and devices, including digitalsnalog. sult
‘eters, funetion generators, oscilloscopes, frequency counters, and
other test and measuring equipment. Aktavox sells a line of test
miters that are popular with professional electricians. The model
‘VC202 i sold through five distributors to retail store inthe United
States, These distributors are located in Atlanta, Boston, Chicago,
Dallas, and Los Angeles and have been selected to serve different
regions inthe country
‘The model C202 has been a steady seller over the years due
silty and rugged construction. Altavox does not consider
Wex 1 2 6
win OS 0
Boston 265 “
Chieago n
Balas 64
u 2 4 ™
a
QUESTIONS
1 Consider using a simple moving average
model. Experiment with models using five
weeks’ 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 I, etc.) Evaluate
the forecasts that would have been made
lover the 13 weeks for each distributor using
the mean absolute deviation, mean absolute
percent errr, and tracking signal as criteria
Altavox Data
woe “5-4-3?
one SS
toton 2B]
Cheo 8 2 RM 4
Oils Sw
w 5 0 4 &
Tool 25453425288
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 spreadsheet Aliavox Date,
‘The demand in the regions varies between a 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 forecast
ing models to determine what should be used in a new system being
implemented. The new system is programmed to use one of two
‘madels: simple moving average or exponential smoothing,
yas) 1213 Avamae
ar 40 0
% @ & 3% 4% 5 8
Byes 8 6 o
6 5 8 6 7 2 8
ee ee)
204 m4 m9 m2
2. Next, consider using a simple exponential smoothing model,
In your analysis, test wo alpha values, 2 and 4. Use the
sec eis ak = bea i
‘Assume tha the initial previous forecast for the model using
am apo valve of i the past three-week: average For the
‘model using an alpha of 4, assume thatthe previous forecast
is the past five-week average,
Altavox. is considering a new option for distributing the
‘model VC202 where, instead of using five distributors, only
8 single distributor would be used. Evaluate this option by
snalyzing how accurate the forecast would be besed 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 tht
should be considered when going from multiple distributors
toa single distributor?
‘This materials only tobe usedin conjunction with MBA lecturesDrax Maxaceaer AND Fonecastine
SuPer Quiz
IL
This is type of forecast used 1o make long-term
decisions such as where to locate a warehouse oF
how many employees o have i & plant next year
This isthe type of demand that is most appropri
ate for using forecasting models
This is a term used for actually influencing the
sale of a product or service,
10
4 Theve are the six major components of demand
5) Thistype of analysis is most appropriate when the
Past isa good predictor ofthe future u
6 This is identifying and separating time series data
into components of demand. R
7 Ifthe demand in the current week was 102 units
and we had forecast it 10 be 125, what would
be next week's forecast using an exponential
smoothing model with an alpha of 0.3?
Assume that you are using exponential smoothing
with an adjustment for trend. Demand is increasing
chapter 15 563
ata very steady rate of about five units per week:
‘Would you expect your alpha and delta parameters
tobe closer to one or ero?
‘Your forecast is, on average, incorrect by about
10 percent. The average demand is 130 units
‘What isthe MAD?
1f the racking signal for your forecast were con
‘istently positive, you could then say this about
your forecasting technique.
‘What would you suggest to improve the forecast
\lescribed in question 102
You know that sales are greatly influenced by the
amount your firm advertises in the local paper.
What forecasting technique would you suggest
tying?
What forecasting fool is most appropriate when
closely working. with customers dependent on
your products?
1. Strategic forecast 2. independent demand 3, Demand management 4, Average demand for the
period, rend, seasonal clements, cyclical elements, random variation, and autocorelation 5. Time
series analysis 6, Decomposition 7.118 units 8. Zero 9. 13 10. Bias, consistently too low 11. Add a
ttend component 12. Causal relationship forecasting (using regression) 13. Collaborative Planning,
recasting, and Replenishment (CPFR)
SELECTED BIBLIOGRAPHY
Diehl FX. Elemento Forcast he, Mason OV South Wester
ove Upper Sule ne ND Perce a St
Footnotes
1 Inaddiono dependent an nepenent dence atone alee complementary products cas elaioaships
2 An emution forthe sand ene tat coin eer compu 5, = VEE
3 Some water refer cal Fa amoathd aerge
4 Shen expe sang sre ince the i oe stating point may be obtained by sng simple ema
ran aerage of peccuig prods such the average of he at 0 ee peo
'5 Special hanks to Gene Feder or lp with his section. Gene Pet “Hiascl Foren: bes and Use Gulieioes”
Indl Managemen! & Dot Stns 10.1200 pp. 512
6 Marshall Fsber “What Is the Right Supply Chain for Your Pret” Hervant Busnss Review March-Apeit 1997,
pp is,
Maik 8; S.C. Wheelwright and RJ, Hyman. Forecast:
‘Metods for Management New Yor: ibn Whey & Sens, 198,