FORECASTING

1. Historical demand for a product is

3-month MA WMA (0.6, 0.3, ES (alpha = 0.2) Absolute Error

Months Demand 0.1)
January 12
February 11 12 11-12=-1
0.2*11+0.8*12 15-11.8=3.2
March 15 12+0.2*(11-12)=11.8
April 12 0.2*15+0.8*11.8
May 16
June 15
July

a. Using a weighted moving average with weights of 0.60, 0.30 and 0.10, find the July
forecast.
b. Using a simple three-month moving average, find the July forecast
c. Using single exponential smoothing with α=0.2 and a June forecast=13, find the July
forecast. Make whatever assumptions you wish
d. Using simple linear regressions analysis, calculate the regression equation for the
preceding demand data.
n ∑ xy−∑ x ∑ y
b=
n ∑ x −( ∑ x )
2 2

a=Y −b x
e. Using the regressions equation in d, calculate the forecast for July.

2. The following tabulations are actual sales of units for six months and a starting forecast
in January.
a. Calculate forecasts for the remaining five months using simple exponential
smoothing with α=0.2
b. Calculate MAD for the forecasts

Forecas
Months Actual t
January 100 80
February 94
March 106
April 80
May 68
June 94
3. The following table shows the past two years of quarterly sales information. Assume
that there are both trend and seasonal factors and that the seasonal cycle is one year.
Use time series decomposition to forecast quarterly sales for the next year.

Quarter Sales
1 160
2 195
3 150
4 140
5 215
6 240
7 205
8 190

4. Here are the actual tabulated demands for an item for a nine-month period (Jan
through Sep) your supervisor wants to test two forecasting methods to see which
method was better over this period.
Months Actual
January 110
February 130
March 150
April 170
May 160
June 180
July 140
August 130
Septemb
er 140

a. Forecast April through September using a three-month average

b. Use simple exponential smoothing with an alpha of .3 to estimate April through
September
c. Use MAD to decide which method produced the better forecast over the six-month
period
5. Historical demand for a product is
Deman
Months d
April 60
May 55
June 75
July 60
August 80
Septemb
er 75

a. Using a simple four-month average, calculate a forecast for October

b. Using single exponential smoothing with α=0.2 and a September forecast =65,
calculate a forecast for October
c. Using simple linear regression, calculate the trend line for the historical data. Say the
X axis is April=1, May=2 and so on, while the Y axis demand.
d. Calculate a forecast for October

6. Use regression analysis on deseasonalized demand to forecast demand in all quarters of

2008, given the following historical demand data

Actual
Year Season Demand
2006 Spring 205
Summe
  r 140
  Fall 375
  Winter 575
2007 Spring 475
Summe
  r 275
  Fall 685
  Winter 965

7. Actual demand for a product for the past three months was
Three months ago 400 units
Two months ago 350 units
 Last month 325 units

a. Using a simple three-month moving average, make a forecast for this month
b. If 300 units were actually demanded this month, what would your forecast be for
next month?
c. Using simple exponential smoothing, what would your forecast be for this month if
the exponentially smoothed forecast for three months ago was 450 units and the
smoothing constant was 0.20?

8. Here are earnings per share for two companies by quarter from the first quarter of 2009
through the second quarter of 2012. Forecast earnings per share for the rest of 2009,
2010 and 2012. Use exponential smoothing to forecast the third period of 2009 and the
time series decomposition method to forecast the last two quarters of 2011 and all four
quarters of 2012. (It is much easier to solve this problem on a computer spreadsheet so
you can see what is happening)

Quarte
  Company A Company B
r
2009 I $1.67 $0.17
  II 2.35 0.24
  III 1.11 0.26
  IV 1.15 0.34
2010 I 1.56 0.25
  II 2.04 0.37
  III 1.14 0.36
  IV 0.38 0.44
2011 I 0.29 0.33
  II -0.18 (loss) 0.4
  III -0.97 (loss) 0.41
  IV 0.2 0.47
2012 I -1.54 (loss) 0.30
  II 0.38 0.47

a. For the exponential smoothing method, choose the first quarter of 2009 as the
beginning forecast. Make two forecasts: one with α=0.10 and one with α=0.30.
b. Using the MAD method of testing the forecasting model’s performance, plus actual
data from 2009 through the second quarter of 2012, how well did the model
perform?
c. Using the decomposition of a Time series method of forecasting, forecast earnings
per share for the last two quarters of 2012 and all four quarters of 2013. Is there a
seasonal factor in the earnings?
d. Using your forecasts, comment on each company.

INVENTORY MANAGEMENT
1) A local newspaper vendor buys newspaper from a local publisher at Rs 2.50 per
paper. He manages to sell this paper at Rs. 5.60 per paper to his customers. Any
paper that the vendor cannot sell can be salvaged at Rs 0.50 per paper. Based on
past data, the demand for paper follows a normal distribution with mean 30 and
standard deviation 10. Given this information, how many papers should the
vendor stock in his store tomorrow morning?

2) Jill’s job shop buys two parts (Tegdiws and Widgets) for use in its production
system from two different suppliers. The parts are needed throughout the year.
Tegdiw are used at a relatively constant rate and are ordered whenever the
remaining quantity drops to the reorder level. Widgets are ordered from a
supplier who stops by every 3 weeks. Data for both products are as follows.

Item Tegdiw Widget

Annual demand 10,000 5,000
Holding cost (% of item 20% 20%
cost)
Setup / order cost $150 $25
Lead time 4 weeks 1 week
Safety stock 55 units 5 units
Item cost $10 $2

a) What is the inventory control system for Tegdiws?

b) What is the inventory control system for Widgets?

3) Sarah’s Muffler shop has one standard muffler that fits a large variety of cars.
Sarah wishes to establish a reorder point system to manage inventory of this
 standard inventory. Use the following information to determine the best order
size and the reorder point.

Annual demand = 3500 mufflers; Ordering cost = $50/order;

Standard deviation of daily demand= 6 mufflers per working day;
Item cost = $30 / muffler; Service probability = 90%;
Lead time = 2 working days; annual holding cost = 25% of item value;
Working days = 300 / year.

MATERIALS REQUIREMENT PLANNING SYSTEM

1) For the example problem solved in class (Electric Meter problem), extend the
materials requirement plan for the periods between 9 and 17 for all 4 items
(Meter A, Meter B, subassembly C and subassembly D).

Week
Item 3 4 5 6 7 8

Meter A Gross Requirement 1250

LT = 2 weeks Scheduled Receipts
On Hand = 50 Projected Available Balance 50 50 50 50 50 0
Safety Stock = 0 Net Requirements 1200
Order qty = lot-for-
lot Planned Order Receipts 1200
Planned Order Releases 1200

Meter B Gross Requirement 470

LT = 2 weeks Scheduled Receipts 10
On Hand = 60 Projected Available Balance 60 60 70 70 70 0
Safety Stock = 0 Net Requirements 400
Order qty = lot-for-
lot Planned Order Receipts 400
Planned Order Releases 400

Subassembly C Gross Requirement 1600

LT = 1 week Scheduled Receipts
On hand = 40 Projected Available Balance 35 35 35 435 435 435
Safety Stock = 5 Net Requirements 1565
Order qty = 2000 Planned Order Receipts 2000
 Planned Order Releases 2000

Subassembly D Gross Requirement 4000 1200 270

LT = 1 week Scheduled Receipts 100
18
On hand = 200 Projected Available Balance 0 280 1280 80 80 4810
Safety Stock = 20 Net Requirements 3720 190
Order qty = 5000 Planned Order Receipts 5000 5000
Planned Order Releases 5000 5000

Projected Available Balance (t) = Projected Available Balance (t-1) + Scheduled Order
Receipts (t) + Planned Order Receipts (t) – Gross Requirement (t)

Net Requirement (t) = Gross Requirement (t) – Projected Available Balance (t-1)

Planned Order Receipt (t) = Net Requirement (t) or a multiple of the order quantity

Planned Order Release (t-l) = Planned Order Receipt (t)