Determining the

Optimal Level of
Product Availability
TI 3207
Supply Chain Management
 1. Identify the factors affecting the optimal level of
product availability and evaluate the optimal
cycle service level
Learning 2. Use managerial levers that improve supply chain
profitability through optimal service levels
Objectives 3. Understand conditions under which
postponement is valuable in a supply chain
4. Allocate limited supply capacity among multiple
products to maximize expected profits
  Product availability measured by cycle service level or fill rate
 Also referred to as the customer service level
 Product availability affects supply chain responsiveness
Importance of
 Trade-off:
the Level  High levels of product availability  increased responsiveness and
of Product higher revenues
 High levels of product availability  increased inventory levels and
Availability higher costs
 Product availability is related to profit objectives and strategic
and competitive issues
 • Cost of overstocking, Co
Factors • Cost of understocking, Cu
Affecting the • Possible scenarios
– Seasonal items with a single order in a season
Optimal Level – One-time orders in the presence of quantity discounts
of Product – Continuously stocked items
– Demand during stockout is backlogged
Availability – Demand during stockout is lost
  L. L. Bean has a buying committee that decides on the quantity of
each product to be ordered. Based on demand over the past few
years, the buyers have estimated the demand distribution for a
women’s red ski parka to be as shown in Table 13-1.

L.L. Bean  The manufacturer also requires that L. L. Bean place orders in
multiples of 100.
Example  In Table 13-1, pi is the probability that demand equals Di, and Pi is
the probability that demand is less than or equal to Di.
 From Table 13-1, we evaluate the expected demand for parkas as
Expected demand = ΣDipi = 1,026
  However, demand is uncertain, and Table 13-1 shows that there is
a 51 percent probability that demand will be 1,000 or less. Thus, a
policy of ordering a thousand parkas results in a cycle service level
of 51 percent at L. L. Bean.
 The buying committee must decide on an order size and cycle
service level that maximize the profits from the sale of parkas at L.
L.L. Bean L. Bean.
Example  The loss that L. L. Bean incurs from an unsold parka and the profit
that it makes on each parka it sells influences the buying decision.
 Each parka costs L. L. Bean c = $45 and is priced in the catalog at p
= $100.
 Any unsold parkas at the end of the season are sold at the outlet
store for $50.
  Holding the parka in inventory and transporting it to the outlet
store costs L. L. Bean $10.
 Thus, L. L. Bean recovers a salvage value of s = $40 for each parka
that is unsold at the end of the season.
 L. L. Bean makes a profit of p - c = $55 on each parka it sells and
incurs a loss of c - s = $5 on each unsold parka that is sold at the
L.L. Bean outlet store.
Example  To decide whether to order 1,100 parkas, the buying committee
must determine the impact of buying the extra 100 units.
 If 1,100 parkas are ordered, the extra 100 are sold (for a profit of
$5,500) if demand is 1,100 or higher.
 Otherwise, the extra 100 units are sent to the outlet store at a loss
of $500.
 Table 13-1

Demand Di Probability Cumulative Probability of Probability of Demand

(in hundreds) pi Demand Being Di or Less (Pi) Being Greater than Di
4 0.01 0.01 0.99
5 0.02 0.03 0.97
6 0.04 0.07 0.93
7 0.08 0.15 0.85
8 0.09 0.24 0.76

L.L. Bean 9
10
0.11
0.16
0.35
0.51
0.65
0.49
Example 11
12
0.20
0.11
0.71
0.82
0.29
0.18
13 0.10 0.92 0.08
14 0.04 0.96 0.04
15 0.02 0.98 0.02
16 0.01 0.99 0.01
17 0.01 1.00 0.00
 Expected demand =å Di pi =1,026

10
Expected profit =å éëDi ( p – c) – (1,000 – Di )(c – s)ùûpi
i=4
17
+å 1,000( p – c) pi =$49,900
L.L. Bean i=11

Example Expected profit

from extra 100 parkas = 5,500 x Prob(demand ≥ 1,100) – 500
x Prob(demand < 1,100)
= $5,500 x 0.49 – $500 x 0.51 = $2,440

Expected profit from

ordering 1,300 parkas = $49,900 + $2,440 + $1,240 + $580
= $54,160
 Additional Expected Marginal Expected Marginal Expected Marginal
Hundreds Benefit Cost Contribution
11th 5,500 x 0.49 = 2,695 500 x 0.51 = 255 2,695 – 255 = 2,440
12th 5,500 x 0.29 = 1,595 500 x 0.71 = 355 1,595 – 355 = 1,240
13th 5,500 x 0.18 = 990 500 x 0.82 = 410 990 – 410 = 580

L.L. Bean 14th 5,500 x 0.08 = 440 500 x 0.92 = 460 440 – 460 = –20
15th 5,500 x 0.04 = 220 500 x 0.96 = 480 220 – 480 = –260
Example 16th 5,500 x 0.02 = 110 500 x 0.98 = 490 110 – 490 = –380
17th 5,500 x 0.01 = 55 500 x 0.99 = 495 55 – 495 = –440

Table 13-2
 Figure 13-1

L.L. Bean
Example

fr =1´ Prob(demand £1,300) + å (1,300 / Di ) pi =0.99

Di >1,300
 Co: Cost of overstocking by one unit, Co = c – s
Cu: Cost of understocking by one unit, Cu = p – c
CSL*: Optimal cycle service level
Optimal Cycle O*: Corresponding optimal order size

Service Level
Expected benefit of purchasing extra unit = (1 – CSL*)(p – c)
for Seasonal
Items – Single Expected cost of purchasing extra unit = CSL*(c – s)
Order
Expected marginal
contribution of raising = (1 – CSL*)(p – c) – CSL*(c – s)
order size
 p–c Cu 1
CSL* =Prob(Demand £O*) = = =
Optimal Cycle p – s Cu + Co 1+ Co / Cu ( )
Service Level
for Seasonal O* =F –1(CSL*, m ,s ) =NORMINV (CSL*, m,s )
Items – Single
Order æO – m ö æO – m ö
Expected profit =( p – s)m Fs ç ÷– ( p – s)s f s ç ÷
è s ø è s ø
–O(c – s)F(O, m,s ) + O( p – c) éë1– F(O, m,s )ùû
 Expected profits =( p – s)m NORMDIST é
ë(O – m ) / s ,0,1,1ù
û
–( p – s)s NORMDIST éë(O – m ) / s ,0,1,0ùû
Optimal Cycle –O(c – s)NORMDIST (O, m,s ,1)
Service Level +O( p – c) é
ë1– NORMDIST (O, m,s ,1ù
û
for Seasonal
Items – Single
Order
 The manager at Sportmart, a sporting goods store, has to decide
Evaluating the on the number of skis to purchase for the winter season. Based
on past demand data and weather forecasts for the year,
Optimal management has forecast demand to be normally distributed,
with a mean of m = 350 and a standard deviation of s = 100. Each
Service Level pair of skis costs c = $100 and retails for p = $250. Any unsold skis
for Seasonal at the end of the season are disposed of for $85. Assume that it
costs $5 to hold a pair of skis in inventory for the season. How
Items many skis should the manager order to maximize expected
profits?
 Demand m = 350, s = 100, c = $100, p = $250,
disposal value = $85, holding cost = $5
Salvage value = $85 – $5 = $80
Evaluating the Cost of understocking = Cu = p – c = $250 – $100 = $150
Optimal Cost of overstocking = Co = c – s = $100 – $80 = $20
Service Level
Cu 150
for Seasonal CSL* =Prob(Demand £O*) = = =0.88
Cu + Co 150 + 20
Items
O* =NORMINV (CSL*, m ,s ) =NORMINV (0.88,350,100) =468
 Expected profits =( p – s)m NORMDIST é
ë(O – m ) / s ,0,1,1ù
û
–( p – s)s NORMDIST é ù
ë(O – m) / s ,0,1,0û
–O(c – s)NORMDIST (O, m,s ,1)
Evaluating the
+O( p – c) é ù
ë1– NORMDIST (O, m,s ,1û
Optimal
Service Level =59,500NORMDIST(1.18,0,1,1)
for Seasonal –17,000NORMDIST (1.18,0,1,0)
–9,360NORMDIST (468,350,100,1)
Items
+70,200 é ù
ë1– NORMDIST (468,350,100,1)û
=$49,146
 Expected =(O – m )F æO – m ö+ s f æO – m ö
Sç ÷ Sç ÷
overstock è s ø è s ø
Expected =(O – m )NORMDIST é(O – m) / s ,0,1,1ù
Evaluating the overstock ë û
+s NORMDIST é ù
ë(O – m) / s ,0,1,0û
Optimal
Service Level Expected =(m – O) é1– F æO – m öù+ s f æO – m ö
ê Sç ÷ú Sç ÷
for Seasonal understock ë è s øû è s ø
Items Expected =(m – O) é1– NORMDIST é(O – m) / s ,0,1,1ùù
understock ë ë ûû
+s NORMDIST éë(O – m ) / s ,0,1,0ù
û
Evaluating
Demand for skis at Sportmart is normally distributed
Expected with a mean of m = 350 and a standard deviation of s =
Overstock 100. The manager has decided to order 450 pairs of skis
for the upcoming season. Evaluate the expected
and Under- overstock and understock as a result of this policy.
stock
 μ = 350, σ = 100, O = 450
Expected =(O – m)NORMDIST é(O – m) / s ,0,1,1ù
overstock ë û
+s NORMDIST é ù
ë(O – m) / s ,0,1,0û

Evaluating =(450 – 350)NORMDIST é ù

ë(450 – 350) / 100,0,1,1û
Expected +100NORMDIST é ù
ë(450 – 350) / 100,0,1,0û=108
Overstock Expected =(m – O) é1– NORMDIST é(O – m) / s ,0,1,1ùù
and Under- understock ë ë ûû
stock +s NORMDIST é ù
ë(O – m) / s ,0,1,0û
=(350 – 450) é
ë1– NORMDIST é(450 – 350) / 100,0,1,1ùù
ë ûû
+100NORMDIST é ù
ë(450 – 350) / 100,0,1,0û=8
 1. Using Co = c – s and Cu = p – c, evaluate the optimal cycle
service level CSL* and order size O* without a discount
• Evaluate the expected profit from ordering O*
One-Time
2. Using Co = cd – s and Cu = p – cd, evaluate the optimal cycle
Orders in the service level CSL*d and order size O*d with a discount
Presence • If O*d ≥ K, evaluate the expected profit from ordering O*d
of Quantity • If O*d < K, evaluate the expected profit from ordering K units

Discounts 3. Order O* units if the profit in step 1 is higher

• If the profit in step 2 is higher, order O*d units if O*d ≥ K or K units if
O*d < K
 SparesRUs, an auto parts retailer, must decide on the order
size for a 20-year-old model of brakes. The manufacturer
Evaluating plans to discontinue production of these brakes after this last
production run. SparesRUs has forecast remaining demand
Service Level for the brakes to be normally distributed, with a mean of 150
and a standard deviation of 40. The brakes have a retail price
with Quantity of $200. Any unsold brakes are useless and have no salvage
Discounts value. The manufacturer plans to sell each brake for $50 if the
order is for less than 200 brakes and $45 if the order is for at
least 200 brakes. How many brakes should SparesRUs order?
 • Step 1, c = $50
Cost of understocking = Cu = p – c = $200 – $50 = $150
Cost of overstocking = Co = c – s = $50 – $0 = $50
Evaluating
Cu 150
Service Level CSL* =Prob(Demand £ O*) = = =0.75
Cu + Co 150 + 50
with Quantity
Discounts O* =NORMINV (CSL*, m ,s ) =NORMINV (0.75,150,40) =177

Expected profit from ordering 177 units = $19,958

 • Step 2, c = $45
Cost of understocking = Cu = p – c = $200 – $45 = $155
Cost of overstocking = Co = c – s = $45 – $0 = $45
Evaluating
Cu 150
Service Level CSL* =Prob(Demand £ O*) = =
Cu + Co 150 + 45
=0.775
with Quantity
Discounts O* =NORMINV (CSL*, m,s ) =NORMINV (0.775,150,40) =180

Expected profit from ordering 200 units = $20,595

Desired Cycle Two extreme scenarios
1. All demand that arises when the product is out of stock
Service Level is backlogged and filled later, when inventories are
for replenished
2. All demand arising when the product is out of stock is
Continuously lost
Stocked Items
 Q: Replenishment lot size
S: Fixed cost associated with each order
ROP: Reorder point
Desired Cycle D: Average demand per unit time
Service Level σ: Standard deviation of demand per unit time
for ss: Safety inventory (ss = ROP – DL)
Continuously CSL: Cycle service level
Stocked Items C: Unit cost
h: Holding cost as a fraction of product cost per unit time
H: Cost of holding one unit for one unit of time. H = hC
 Increased cost per replenishment cycle
of additional safety inventory of 1 unit = (Q > D)H

Benefit per replenishment cycle of

Demand additional safety inventory of 1 unit = (1 – CSL)Cu
During Stock- é HQ ù
CSL* =1– ê ú
out is ëDCu û
Backlogged
 Weekly demand for detergent at Walmart is normally
distributed, with a mean of D = 100 gallons and a
Demand standard deviation of σD = 20. The replenishment lead
time is L = 2 weeks. The store manager at Walmart
During Stock- orders 400 gallons when the available inventory drops to
out is 300 gallons. Each gallon of detergent costs $3. The
holding cost Walmart incurs is 20 percent. If all unfilled is
Backlogged backlogged and carried over to the next cycle, evaluate
the cost of stocking out implied by the current
replenishment policy.
 Lot size, Q = 400 gallons
Reorder point, ROP = 300 gallons
Average demand per year, D = 100 x 52 = 5,200
Standard deviation of demand per week, sD = 20
Demand Unit cost, C = $3
During Stock- Holding cost as a fraction of product cost per year, h = 0.2
out is Cost of holding one unit for one year, H = hC = $0.6
Lead time, L = 2 weeks
Backlogged Mean demand over lead time, DL = 200 gallons
Standard deviation of demand over lead time, s =s D L
L

=20 2 =28.3
 CSL =F(ROP, DL ,s L ) =NORMDIST (300,200,28.3,1) =0.9998

HQ 0.6 ´ 400
Demand Cu = = =$230.8 per gallon
(1– CSL)D 0.0002 ´ 5,200
During Stock-
out is
Backlogged
Evaluating
Optimal Consider the situation in previous Example but make the
Service Level assumption that all demand during a stock-out is lost.
Assume that the cost of losing one unit of demand is $2.
When Unmet Evaluate the optimal cycle service level that the store
Demand Is manager at Walmart should target.

Lost
 Lot size, Q = 400 gallons
Average demand per year, D = 100 x 52 = 5,200
Evaluating Cost of holding one unit for one year, H = $0.6
Optimal Cost of understocking, Cu = $2
Service Level HQ
When Unmet CSL* =1–
HQ + DCu
Demand Is 0.6 ´ 400
=1– =0.98
Lost 0.6 ´ 400 + 2 ´ 5,200
  “Obvious” actions
1. Increase salvage value of each unit
Managerial 2. Decrease the margin lost from a stock-out
Levers to  Improved forecasting
Improve  Quick response
Supply Chain  Postponement
Profitability  Tailored sourcing
Managerial
Levers to
Improve
Supply Chain
Profitability

Figure 13-2
  Improved forecasts result in reduced uncertainty
 Less uncertainty results in
 Lower levels of safety inventory (and costs) for the same level
Improved of product availability, or
 Higher product availability for the same level of safety
Forecasts inventory, or
 Both
 Consider a buyer at Bloomingdale’s who is responsible for
purchasing dinnerware with Christmas patterns. The
dinnerware sells only during the Christmas season, and the
buyer places an order for delivery in early November. Each
dinnerware set costs c = $100 and sells for a retail price of p =
Impact of $250. Any sets unsold by Christmas are heavily discounted in
the post-Christmas sales and are sold for a salvage value of s =
Improved $80. The buyer has estimated that demand is normally
Forecasts distributed, with a mean of m = 350. Historically, forecast
errors have had a standard deviation of s = 150. The buyer has
decided to conduct additional market research to get a better
forecast. Evaluate the impact of improved forecast accuracy
on profitability and inventories as the buyer reduces s from
150 to 0 in increments of 30.
 Demand: m = 350,  = 150
Cost: c = $100, Price: p = $250, Salvage: s = $80

Cost of understocking =Cu = p – c =$250 – $100 =$150

Impact of Cost of overstocking =Co =c – s =$100 – $80 =$20
Improved
Forecasts 150
CSL* =Prob(Demand £ O*) ³ =0.88
150 + 20
 Standard
Deviation of Optimal
Forecast Order Expected Expected Expected
Error σ Size O* Overstock Understock Profit
150 526 186.7 8.6 $47,469

Impact of 120 491 149.3 6.9 $48,476

90 456 112.0 5.2 $49,482
Improved 60 420 74.7 3.5 $50,488
Forecasts 30 385 37.3 1.7 $51,494
0 350 0 0 $52,500

Table 13-3
Impact of
Improved
Forecasts

Figure 13-3
  Set of actions taken by managers to reduce
replenishment lead time
Quick  Reduced lead time results in improved forecasts
Response:  Benefits
Impact on  Lower order quantities thus less inventory with same
product availability
Profits and  Less overstock
Inventories  Higher profits
 • Ordering shawls at a department store
– Selling season = 14 weeks
Quick – Cost per shawl = $40
– Retail price = $150
Response: – Disposal price = $30
Multiple – Holding cost = $2 per week
– Expected weekly demand D = 20
Orders Per – Standard deviation sD = 15
Season
 Two ordering policies
Quick 1. Supply lead time is more than 15 weeks
 Single order placed at the beginning of the season
Response:  Supply lead time is reduced to six weeks

Multiple 2. Two orders are placed for the season

 One for delivery at the beginning of the season
Orders Per  One at the end of week 1 for delivery in week 8

Season
 Expected demand =m =14D =14 ´ 20 =280
Standard deviation =s = 14s D = 14 ´ 15 =56.1

p – c 150 – 40
Single Order CSL* = = =0.92
p – s 150 – 30
Policy
O* =NORMINV (CSL*, m,s ) =NORMINV (0.92,280,56.1) =358
 Expected profit with a single order = $29,767
Expected overstock = 79.8
Expected understock = 2.14
Cost of overstocking = $10
Single Order Cost of understocking = $110
Policy
Expected cost of overstocking = 79.8 x $10 = $798
Expected cost of understocking = 2.14 x $110 = $235
 Expected demand =m7 =7 ´ 20 =140
Standard deviation =s 7 = 7 ´ 15 =39.7

O1 =NORMINV (CSL*, m 7 ,s 7 ) =NORMINV (0.92,140,39.7) =195

Two Order
Expected profit from seven weeks = $14,670
Policy
Expected overstock = 56.4
Expected understock = 1.51

cted profit from season = $14,670 + 56.4

x $10 + $14,670
= $29,904
 Three important consequences
1. The expected total quantity ordered during the
Quick season with two orders is less than that with a single
Response: order for the same cycle service level
Multiple 2. The average overstock to be disposed of at the end
of the sales season is less if a follow-up order is
Orders Per allowed after observing some sales
Season 3. The profits are higher when a follow-up order is
allowed during the sales season
Quick
Response:
Multiple
Orders Per
Season

Figure 13-4
Quick
Response:
Multiple
Orders Per
Season

Figure 13-5
 Expected demand =m7 =7 ´ 20 =140
Standard deviation first 7 weeks =s 7 = 7 ´ 15 =39.7
Two Order Standard deviation second 7 weeks =s 72 = 7 ´ 3 =7.9
Policy with O2 =NORMINV (CSL*, m 7 ,s 72 ) =NORMINV (0.92,140,7.9) =151
Improved Expected profit from second order = $15,254
Forecast Expected overstock = 11.3
Accuracy Expected understock = 0.30
xpected profit from season = $14,670 + 56.4
x $10 + $15,254
= $30,488
  Delay of product differentiation until closer to the
sale of the product
 Activities prior to product differentiation require
aggregate forecasts more accurate than individual
Postponement product forecasts
: Impact on  Individual product forecasts are needed close to the
Profits and time of sale
Inventories  Results in a better match of supply and demand
 Valuable in online sales
 Higher profits through better matching of supply and
demand
  The production process at Benetton, where assembled knit garments
are dyed, costs about 10 percent more than if dyed thread is knitted.
 Similarly, when retailers mix paint at stores rather than at the factory,
manufacturing costs increase because there is a loss of economies of
scale in mixing.
Value of  We illustrate this using the example of Benetton selling knit garments
Postponement in solid colors.
 Starting with thread, two steps are needed to complete the garment -
: Benetton dyeing and knitting.
 Traditionally, thread was dyed and then the garment was knitted
(Option 1).
 Benetton developed a procedure whereby dyeing was postponed
until after the garment was knitted (Option 2)
  Benetton sells each knit garment at a retail price p = $50.
 Option 1 (no postponement) results in a manufacturing cost of $20,
whereas Option 2 (postponement) results in a manufacturing cost of
$22 per garment.
Value of  Benetton disposes of any unsold garments at the end of the season in
a clearance for s = $10 each.
Postponement  The knitting or manufacturing process takes a total of 20 weeks.
: Benetton  For the sake of discussion, we assume that Benetton sells garments in
four colors.
 Twenty weeks in advance, Benetton forecasts demand for each color
to be normally distributed, with a mean of m = 1,000 and a standard
deviation of s = 500.
  Demand for each color is independent.
 With Option 1, Benetton makes the buying decision for each color 20
weeks before the sale period and holds separate inventories for each
Value of color.
 With Option 2, Benetton forecasts only the aggregate uncolored
Postponement thread to purchase 20 weeks in advance.
: Benetton  The inventory held is based on the aggregate demand across all four
colors.
 Benetton decides the quantity for individual colors after demand is
known.
 For each of four colors

Demand m = 1,000, s = 50,

Value of Sale price p = $50, Salvage value s = $10
Postponement
Production cost Option 1 (no postponement) = $20
: Benetton
Production cost Option 2 (postponement) = $22
  Option 1, for each color

p – c 30
CSL* = = =0.75
p – s 40
Value of
O* =NORMINV (CSL*, m,s ) =NORMINV (0.75,1000,500) =1,337
Postponement
: Benetton Expected profits = $23,664
Expected overstock = 412
Expected understock = 75
Total production = 4 x 1,337 = 5,348
Expected profit = 4 x 23,644 = $94,576
  Option 2, for all sweaters

p – c 28
CSL* = = =0.70
p – s 40
Value of m A =4 ´ 1,000 =4,000 s A = 4 ´ 500 =1,000
Postponement OA* =NORMINV (0.7, m A ,s A ) =NORMINV (0.7,4000,1000) =4,524
: Benetton
Expected profits = $98,092
Expected overstock = 715
Expected understock = 190
 • Postponement is not very effective if a large fraction
of demand comes from a single product
• Option 1
Red sweaters demand mred = 3,100, sred = 800
Value of Other colors m = 300, s = 200
Postponement *
Ored =NORMINV (CSL*, mred ,s red )
: Benetton =NORMINV (0.75,3100,800) =3,640
Expected profitsred = $82,831
Expected overstock = 659
Expected understock = 119
 Other colors m = 300, s = 200
O* =NORMINV (CSL*, m,s ) =NORMINV (0.75,300,200) =435

Expected profitsother = $6,458

Value of Expected overstock = 165

Expected understock = 30
Postponement
: Benetton Total production = 3,640 + 3 x 435 = 4,945
Expected profit = $82,831 + 3 x $6,458 = $102,205
Expected overstock = 659 + 3 x 165 = 1,154
Expected understock = 119 + 3 x 30 = 209
  Option 2
m A =3,100 + 3 ´ 300 =4,000
s A = 8002 + 3 ´ 2002 =872
Value of
Postponement Total production = 4,475
: Benetton Expected profit = $99,872
Expected overstock = 623
Expected understock = 166
 • Use production with postponement to satisfy a
part of demand, the rest without postponement
• Produce red sweaters without postponement,
Tailored postpone all others
Postponement Profit = $103,213
: Benetton • Tailored postponement allows a firm to increase
profits by postponing differentiation only for
products with uncertain demand
  Separate all demand into base load and variation
 Base load manufactured without postponement
 Variation is postponed

Four colors
Tailored Demand mean μ = 1,000, σ = 500
Postponement
 Identify base load and variation for each color
: Benetton
 Table 13-4

Manufacturing Policy
Average Average Average
Q1 Q2 Profit Overstock Understock
0 4,524 $97,847 510 210
1,337 0 $94,377 1,369 282

Tailored 700 1,850 $102,730 308 168

800 1,550 $104,603 427 170
Postponement 900 950 $101,326 607 266
: Benetton 900 1,050 $101,647 664 230
1,000 850 $100,312 815 195
1,000 950 $100,951 803 149
1,100 550 $99,180 1,026 211
1,100 650 $100,510 1,008 185
  A firm uses a combination of two supply sources
 One is lower cost but is unable to deal with
uncertainty well
 Second more flexible but is higher cost
Tailored
 Focus on different capabilities
Sourcing
 Increase profits, better match supply and
demand
 May be volume based or product based
Setting  Consider a department store that plans to order two styles of
sweaters from an Italian supplier.
Product  Demand for the high-end sweater is forecast to be normally
Availability for distributed, with a mean of m1 = 1,000 and a standard deviation of
s1 = 300.
Multiple  Demand for the mid-range sweater is normally distributed, with a
Products mean of m2 = 2,000 and a standard deviation of s2 = 400.

Under  The high-end sweater has a retail price of p1 = $150, a cost c1 =

$50, and a salvage value of s1 = $35.
Capacity  The mid-range sweater has a retail price of p2 = $100, a cost c2 =
Constraints $40, and a salvage value of s2 = $25
  Two styles of sweaters from Italian supplier
Setting High end Mid-range
Product m1 = 1,000 m2 = 2,000
Availability for s1 = 300 s2 = 400
Multiple p1 = $150 p2 = $100
Products c1 = $50 c2 = $40
Under s1 = $35 s2 = $25
Capacity CSL = 0.87 CSL = 0.80
Constraints O = 1,337 O = 2,337
  Supplier capacity constraint, 3,000 units
Setting Expected marginal =MC1(1,000)
Product contribution high-end
= p1 é
ë1– F1
(1,000)ù+ s F (1,000) – c
û 1 1 1
Availability for =150 ´ (1– 0.5) + 35 ´ 0.5 – 50
Multiple =$42.50
Products Expected marginal =MC2 (1,999)
Under contribution mid-range
= p2 é
ë1– F (1,999)ù+ s F (1,999) – c
û 2 2
Capacity 2 2

Constraints =100 ´ (1– 0.499) + 25 ´ 0.499 – 40

=$22.57
 MCi (Qi ) = pi é
ë1– Fi
(Q ù+ s F (Q ) – c
i) û i i i i

Setting 1. Set quantity Qi = 0 for all products i

Product 2. Compute the expected marginal contribution MCi(Qi) for each
product i
Availability for 3. If positive, stop, otherwise, let j be the product with the highest
Multiple expected marginal contribution and increase Qj by one unit
4. If the total quantity is less than B, return to step 2, otherwise
Products capacity constraint are met and quantities are optimal
Under n

åQ
n subject to:
Capacity £B
Maxå Õ i (Qi ) i
i=1
Constraints i=1
Qi ³ 0
 Expected Marginal Contribution Order Quantity
Capacity Left High End Mid Range High End Mid Range

Setting 3,000
2,900
99.95
99.84
60.00
60.00
0
100
0
0

Product 2,100
2,000
57.51
57.51
60.00
60.00
900
900
0
100
Availability for 800 57.51 57.00 900 1,300
780 54.59 57.00 920 1,300
Multiple 300 42.50 43.00 1,000 1,700

Products 200
180
42.50
39.44
36.86
36.86
1,000
1,020
1,800
1,800

Under 40
30
31.89
30.41
30.63
30.63
1,070
1,080
1,890
1,890
Capacity 10 29.67 29.54 1,085 1,905
1 29.23 29.10 1,088 1,911
Constraints 0 29.09 29.10 1,089 1,911

Table 13-5
Setting
Optimal 1. Beware of preset levels of availability
2. Use approximate costs because profit-maximizing solutions
Levels of are quite robust
Product 3. Estimate a range for the cost of stocking out
Availability in 4. Tailor your response to uncertainty

Practice
 1. Identify the factors affecting the optimal level of
product availability and evaluate the optimal cycle
service level
Summary of 2. Use managerial levers that improve supply chain
Learning profitability through optimal service levels
Objectives 3. Understand conditions under which
postponement is valuable in a supply chain
4. Allocate limited supply capacity among multiple
products to maximize expected profits
End of Topic
TI 3207
Supply Chain Management
 Green Thumb, a manufacturer of lawn care equipment, has
introduced a new product. Each unit costs $150 to
manufacture, and the introductory price is $200. At this price,
the anticipated demand is normally distributed, with a mean
of m = 100 and a standard deviation of s = 40. Any unsold units
at the end of the season are unlikely to be valuable and will be
Exercise 1 disposed of in a post-season sale for $50 each. It costs $20 to
hold a unit in inventory for the entire season. How many units
should Green Thumb manufacture for sale? What is the
expected profit from this policy? On average, how many
customers does Green Thumb expect to turn away because of
stocking out?
 Champion manufactures winter fleece jackets for sale in the United
States. Demand for jackets during the season is normally distributed,
with a mean of 20,000 and a standard deviation of 10,000. Each jacket
sells for $60 and costs $30 to produce. Any leftover jackets at the end
of the season are sold for $25 at the year-end clearance sale. Holding
jackets until the year-end sale adds another $5 to their cost. A recent
recruit has suggested shipping leftover jackets to South America for
Exercise 2 sale in the winter there rather than running a clearance. Each jacket
will fetch a price of $35 in South America, and all jackets sent there are
likely to sell. Shipping costs add $5 to the cost of any jacket sold in
South America. Would you recommend the South American option?
How will this decision affect production decisions at Champion? How
will it affect profitability? On average, how many jackets will
Champion ship to South America each season?
 Daily demand for aspirin at DoorRed Pharmacy is normally
distributed, with a mean of 40 bottles and a standard deviation of 5.
The replenishment lead time from the supplier is one day. The
current inventory policy at DoorRed is to order 200 bottles when the
quantity on hand drops below 45. Each bottle costs DoorRed $4,
and the pharmacy uses a holding cost of 25 percent.
a. If all unfilled demand is assumed to be backlogged and carried
Exercise 3 over to the next cycle, what cost of understocking justifies the
current policy?
b. If all unfilled demand is assumed to be lost, what cost of
stocking out justifies the current policy?
c. DoorRed believes that all unfilled demand can be backlogged if
customers are given a $1.50 discount on their next purchase
(effectively making the cost of understocking $1.50). What
inventory policy do you recommend for DoorRed?
 The Knitting Company (TKC) is planning production for its our sweater styles that are
popular during Christmas. All four styles have demand that is normally distributed. The
best-selling style has an expected demand of 30,000 and a standard deviation of 5,000.
Each of the other three styles has an expected demand of 10,000 with a standard
deviation of 4,000. Currently, all sweaters are produced before the start of the season.
Production cost is $20 per sweater, and they are sold for a wholesale price of $35. Any
unsold sweaters at the end of the season are discounted to $15, and they all sell at that
price. It costs $2 to hold the sweater in inventory for the entire season if it does not sell.
a. How many sweaters of each type should TKC manufacture?
Exercise 4 b. What is the expected profit from this policy?
c. How many sweaters does TKC expect to sell at a discount?
d. TKC is considering the postponement of knitting and using flexible machines. This
will require the base sweaters to be made in advance (identical for each of the four
types) and the final patterns to be knit later. This will increase production cost per
sweater to $21.40. How many sweaters should TKC manufacture with
postponement? What is the expected profit from this policy?
e. Another option is to produce the popular style without postponement and the other
three styles using postponement. What is the expected profit under this policy?