CHAPTER 15: INVENTORY MODELS

Outline

• Deterministic models
– The Economic Order Quantity (EOQ) model
– Sensitivity analysis
– A price-break Model
• Probabilistic Inventory models
– Single-period inventory models
– A fixed order quantity model
– A fixed time period model

1
 Inventory Decision Issues

• Demand of various items

• Money tied up in the inventory
• Cost of storage space
• Insurance expense - risk of fire, theft, damage
• Order processing costs
• Loss of profit due to stock outs

2
Inventory Decision Questions

How Much?
When?

3
 THE EOQ MODEL

Demand
Order qty, Q
Inventory Level
rate

Reorder point, R

0 Lead Lead Time

time time
Order Order Order Order
Placed Received Placed Received
4
 The EOQ Model Cost Curves

Slope = 0
Annual Total Cost
cost ($)

Minimum
total cost
Holding Cost = HQ/2

Ordering Cost = SD/Q

Optimal order Q* Order Quantity, Q

5
 EOQ Cost Model

D - annual demand
Q - order quantity * 2 DS
S - cost of placing order Q 
H - annual per-unit holding cost H
Ordering cost = SD/Q
Holding cost = HQ/2

Total cost = SD/Q + HQ/2

6
Example 1: R & B beverage company has a soft drink
product that has a constant annual demand rate of 3600
cases. A case of the soft drink costs R & B $3. Ordering
costs are $20 per order and holding costs are 25% of the
value of the inventory. R & B has 250 working days per
year, and the lead time is 5 days. Identify the following
aspects of the inventory policy:
a. Economic order quantity

7
b. Reorder point

c. Cycle time

8
d. Total annual cost

9
 SENSITIVITY ANALYSIS

Cost
Opt with
D I S Q* Cost Q=438
3600 25% 20 438 329 329
3400 25% 20 426 319 320
3600 35% 20 370 389 394
3600 25% 30 537 402 411
10
 Some Important Characteristics of the EOQ
Cost Function

• At EOQ, the annual holding cost is the same as annual

ordering cost.
HQ* H 2 DS DSH
Annual holding cost   
2 2 H 2
DS DS DSH
Annual ordering cost  *
 
Q 2 DS 2
H
HQ* DS
Total annual cost   *  2 DSH
2 Q
11
 Some Important Characteristics of the EOQ
Cost Function

• The total cost curve is flat near EOQ

– So, the total cost does not change much with a slight
change in the order quantity (see the total cost curve
and the example on sensitivity)

12
 EOQ WITH PRICE BREAKS

• Assumptions
– Demand occurs at a constant rate of D items per
year.
– Ordering Cost is $S per order.
– Holding Cost is $H = $CiI per item in inventory per
year (note holding cost is based on the cost of the
item, Ci).
– Purchase Cost is $C1 per item if the quantity ordered
is between 0 and x1, $C2 if the order quantity is
between x1 and x2, etc.
– Delivery time (lead time) is constant.

13
 EOQ with Price Breaks Formulae

• Formulae

– Optimal order quantity: the procedure for

determining Q* will be demonstrated
– Number of orders per year: D/Q*
– Time between orders (cycle time): Q*/D years
– Total annual cost: [(1/2)Q*H] + [DS/Q*] + DC
(holding + ordering + purchase)

14
 EOQ with Price Breaks Procedure

Steps
1. Determine the largest (cheapest) feasible EOQ value:
The most efficient way to do this is to compute the
EOQ for the lowest price first, and continue with the
next higher price. Stop when the first EOQ value is
feasible (that is, within the correct interval).
2. Compare the costs: Compare the value of the
average annual cost at the largest feasible EOQ and
at all of the price breakpoints that are greater than
the largest feasible EOQ. The optimal Q is the point
at which the average annual cost is a minimum.

15
Example 2: Nick's Camera Shop carries Zodiac instant
print film. The film normally costs Nick $3.20 per roll,
and he sells it for $5.25. Nick's average sales are 21
rolls per week. His annual inventory holding cost rate is
25% and it costs Nick $20 to place an order with
Zodiac. If Zodiac offers a 7% discount on orders of 400
rolls or more and a 10% discount for 900 rolls or more,
determine Nick's optimal order quantity.

16
D = 21(52) = 1092; H = .25(Ci); S = 20

Step 1: Determine the largest (cheapest) feasible EOQ

17
Step 2: Compare the costs
Compute the total cost for the most economical, feasible
order quantity in each price category for which a Q* was
computed.

18
 PROBABILISTIC MODELS

Outline

• Probabilistic inventory models

• Single- and multi- period models
• A single-period model with uniform distribution of
demand
• A single-period model with normal distribution of
demand

19
 Probabilistic Inventory Models

• The demand is not known. Demand characteristics

such as mean, standard deviation and the distribution
of demand may be known.
• Stockout cost: The cost associated with a loss of
sales when demand cannot be met. For example, if
an item is purchased at $1.50 and sold at $3.00, the
loss of profit is $3.00-1.50 = $1.50 for each unit of
demand not fulfilled.

20
 Single- and Multi- Period Models

• The classification applies to the probabilistic demand

case
• In a single-period model, the items unsold at the end
of the period is not carried over to the next period.
The unsold items, however, may have some salvage
values.
• In a multi-period model, all the items unsold at the
end of one period are available in the next period.
• In the single-period model and in some of the multi-
period models, there remains only one question to
answer: how much to order.

21
 SINGLE-PERIOD MODEL

• Computer that will be obsolete before the next order

• Perishable product
• Seasonal products such as bathing suits, winter
coats, etc.
• Newspaper and magazine

22
 Trade-offs in a Single-Period Models

Loss resulting from the items unsold

ML= Purchase price - Salvage value

Profit resulting from the items sold

MP= Selling price - Purchase price

Trade-off
Given costs of overestimating/underestimating demand
and the probabilities of various demand sizes
how many units will be ordered?

23
Consider an order quantity Q
Let P = probability of selling all the Q units
= probability (demandQ)

Then, (1-P) = probability of not selling all the Q units

We continue to increase the order size so long as

P( MP)  (1  P ) ML
ML
or , P 
MP  ML

24
Decision Rule:

Order maximum quantity Q such that

ML
P
MP  ML

where P = probability (demandQ)

25
Text Problem 21, Chapter 15: Demand for cookies:
Demand Probability of Demand
1,800 dozen 0.05
2,000 0.10
2,200 0.20
2,400 0.30
2,600 0.20
2,800 0.10
3,000 0,05
Selling price=$0.69, cost=$0.49, salvage value=$0.29
a. Construct a table showing the profits or losses for each
possible quantity
b. What is the optimal number of cookies to make?
c. Solve the problem by marginal analysis.
26
Demand Prob Prob Expected Revenue Revenue Total Cost Profit
(dozen) (Demand) (Selling Number From From Revenue
all the units) Sold Sold Unsold
Items Items
1800 0.05
2000 0.1
2200 0.2
2400 0.3
2600 0.2
2800 0.1
3000 0.05

Sample computation for order quantity = 2200:

Expected number sold=1800(0.05)+2000(0.10)+2200(0.85)
=2160
Revenue from sold items=2160(0.69)=$1490.4
Revenue from unsold items=(2200-2160)(0.29)=$11.6
Total revenue=1490.4+11.6=$1502
Cost=2200(0.49)=$1078
27
Profit=1502-1078=$424
Demand Prob Prob Expected Revenue Revenue Total Cost Profit
(dozen) (Demand) (Selling Number From From Revenue
all the units) Sold Sold Unsold
Items Items
1800 0.05 1 1800 1242.0 0.0 1242 882 360
2000 0.1 0.95 1990 1373.1 2.9 1376 980 396
2200 0.2 0.85 2160 1490.4 11.6 1502 1078 424
2400 0.3 0.65 2290 1580.1 31.9 1612 1176 436
2600 0.2 0.35 2360 1628.4 69.6 1698 1274 424
2800 0.1 0.15 2390 1649.1 118.9 1768 1372 396
3000 0.05 0.05 2400 1656.0 174.0 1830 1470 360

28
Solution by marginal analysis:
MP  .69  .49  $0.20, ML  .49  .29  $0.20
Order maximum quantity, Q such that
ML 0.20
P  Probabilitydemand  Q     0.50
MP  ML 0.20  0.20
Demand, Q Probability(demand) Probability(demandQ),
p

29
 Demand Characteristics

Suppose that the historical sales data shows:

Quantity No. Days sold Quantity No. Days sold

14 1 21 11
15 2 22 9
16 3 23 6
17 6 24 3
18 9 25 2
19 11 26 1
20 12

30
Demand Characteristics
Mean = 20
Standard deviation = 2.49

31
Demand Characteristics

32
Example 3: The J&B Card Shop sells calendars. The once-
a-year order for each year’s calendar arrives in
September. The calendars cost $1.50 and J&B sells them
for $3 each. At the end of July, J&B reduces the calendar
price to $1 and can sell all the surplus calendars at this
price. How many calendars should J&B order if the
September-to-July demand can be approximated by
a. uniform distribution between 150 and 850

33
Solution to Example 3:

Loss resulting from the items unsold

ML= Purchase price - Salvage value =

Profit resulting from the items sold

MP= Selling price - Purchase price =

34
 ML
P =
MP  ML

Now, find the Q so that P(demandQ) =

Q* =

35
Example 4: The J&B Card Shop sells calendars. The once-
a-year order for each year’s calendar arrives in
September. The calendars cost $1.50 and J&B sells them
for $3 each. At the end of July, J&B reduces the calendar
price to $1 and can sell all the surplus calendars at this
price. How many calendars should J&B order if the
September-to-July demand can be approximated by
b. normal distribution with  = 500 and =120.

36
Solution to Example 4: ML=$0.50, MP=$1.50 (see example 3)

ML
P =
MP  ML

Now, find the Q so that P =

37
We need z corresponding to area =
From Appendix D, p. 780

z=
Hence, Q* =  + z =

38
Example 5: A retail outlet sells a seasonal product for $10
per unit. The cost of the product is $8 per unit. All units not
sold during the regular season are sold for half the retail
price in an end-of-season clearance sale. Assume that the
demand for the product is normally distributed with  =
500 and  = 100.
a. What is the recommended order quantity?
b. What is the probability of a stockout?
c. To keep customers happy and returning to the store
later, the owner feels that stockouts should be avoided if
at all possible. What is your recommended quantity if the
owner is willing to tolerate a 0.15 probability of stockout?
d. Using your answer to part c, what is the goodwill cost
you are assigning to a stockout?
39
Solution to Example 5:
a. Selling price=$10,
Purchase price=$8
Salvage value=10/2=$5
MP =10 - 8 = $2, ML = 8-10/2 = $3
Order maximum quantity, Q such that
ML 3
P   0. 6
ML  MP 2  3
Now, find the Q so that
P = 0.6
or, area (2)+area (3) = 0.6
or, area (2) = 0.6-0.5=0.10

40
Find z for area = 0.10 from the standard normal table given in
Appendix D, p. 736
z = 0.25 for area = 0.0987, z = 0.26 for area = 0.1025
So, z = 0.255 (take -ve, as P = 0.6 >0.5) for area = 0.10
So, Q*=+z =500+(-0.255)(100)=474.5 units.

b. P(stockout) = P(demandQ) = P = 0.6

c. P(stockout)=Area(3)=0.15
From Appendix D,
find z for
Area (2) = 0.5-0.15=0.35

41
z = 1.03 for area = 0.3485
z = 1.04 for area = 0.3508
So, z = 1.035 for area = 0.35
So, Q*=+z =500+(1.035)(100)=603.5 units.

d. P=P(demandQ)=P(stockout)=0.15
For a goodwill cost of g
MP =10 - 8+g = 2+g, ML = 8-10/2 = 3

ML 3
Now, solve g in p =   0.15
ML  MP 2  g  3

Hence, g=$15.

42
 MULTI-PERIOD MODELS

Outline

• A fixed order quantity model

• A fixed time period model

43
 A FIXED ORDER QUANTITY MODEL
Purchase-order can be placed at any time
On-hand inventory count is known always

Lead time for a high speed modem is Will you order

two weeks and it has the following now if number
sales history in the last 25 weeks: of items on
Quantity/Week Frequency hand is:
75-80 1
70-75 3 a. 200
65-70 9 b. 150
60-65 8 c. 100
55-60 4 44
 A Fixed Order Quantity Model

• The same quantity, Q is ordered when inventory on

hand reaches a reorder point, R

45
 A Fixed Order Quantity Model

• An order quantity of EOQ works well

• If demand is constant, reorder point is the same as

the demand during the lead time.

• If demand is uncertain, reorder point is usually set

above the expected demand during the lead time

• Reorder point = Expected demand + Safety stock

46
 Safety Stock
Quantity

Expected demand
during lead time

Reorder Point

Safety stock
Time
Lead Time 47
 Trade-Off with Safety Stock

• Safety Stock - Stock held in excess of expected

demand to protect against stockout during lead time.

Safety stock  Holding cost  Stockouts 

Safety stock  Holding cost  Stockouts 

48
 Acceptable Level of Stockout

Ask the manager!!

Acceptable level of stockout reflects management’s tolerance

A related term is service level.

Example: if 20 orders are placed in a year and management

can tolerate 1 stockout in a year, acceptable level of
stockout = 1/20 = 0.05 = 5% and the service level = 1- 0.05
= 0.95.
49
Computation of Safety Stock

50
Example 6: B&S Novelty and Craft Shop sells a variety of
quality handmade items to tourists. B&S will sell 300
hand-made carved miniature replicas of a Colonial soldier
each year, but the demand pattern during the year is
uncertain. The replicas sell for $20 each, and B&S uses a
15% annual inventory holding cost rate. Ordering costs
are $5 per order, and demand during the lead time follows
a normal probability distribution with  = 15 and  = 6.
a. What is the recommended order quantity?
b. If B&S is willing to accept a stockout roughly twice a
year, what reorder point would you recommend? What is
the probability that B&S will have a stockout in any one
order-cycle?
c. What are the inventory holding and ordering costs?

51
 A FIXED TIME PERIOD MODEL

• Purchase-order is issued at a fixed interval of time

A distributor of soft drinks prepares a purchase order

for beverages once a week on every Monday. The
beverages are received on Thursdays (the lead time is
three days). Choose a method for finding order quantity
for the distributor:
a. Mean demand for 7 days + safety stock
b. Mean demand for 10 days + safety stock
c. Mean demand for 10 days + safety stock — inventory
on hand 52
 Replenishment Level and Safety Stock

• Replenishment level, M
= Desired inventory to cover review period & lead time
= Expected demand during review period & lead time +
Safety stock

• Order quantity, Q = M - H
H = inventory on hand

• Trade-off with safety stock

Safety stock  Holding cost  Stockouts 

Safety stock  Holding cost  Stockouts 53
The Fixed Time Period Model

54
Computation of Replenishment Level

55
 Comparison Between P and Q models

Fi
xed
Quan
tit
y Fi
xedPe
rio
d
A
d
va
nt
age N
otl
ar
ges
af
et
y E a
seo
fcoor
di
nat
i
on,
s
t
ock
,go
odf
or Le
sswo
rk,g
oodf
or
e
xp
ens
iv
ei
te
m. i
nex
pe
nsi
vei
tems
S
afe
t
yst
ock r
L
M 
T
L

Av
er
age
inv
e
nt
or
y, 1
Q
1

r
eg
ul
ar 2 2
T

2
DS
O
r
de
rq
ua
nt
i
ty E
OQ
= -
M
I
H
R
eo
rd
erpo
i
nt r

L 
zL

R
ep
le
ni
shm
ent
lev
el M

T
L
zT
L

A
nn
ua
lnum
berof D 1
o
r
de
rs Q
TTi
sin
ye
ar
s
56
Example 7: Statewide Auto parts uses a 4-week periodic-
review system to reorder parts for its inventory stock. A 1-
week lead time is required to fill the order. Demand for
one particular part during the 5-week replenishment period
is normally distributed with a mean of 18 units and a
standard deviation of 6 units.
a. At a particular periodic review, 8 units are in inventory.
The parts manager places an order for 16 units. What is
the probability that this part will have a stockout before an
order that is placed at the next 4-week review period
arrives?
B. Assume that the company is willing to tolerate a 2.5%
chance of stockout associated with a replenishment
decision. How many parts should the manager have
ordered in part (a)? What is the replenishment level for the
4-week periodic review system?
57
Example 8: Rose Office Supplies, Inc., uses a 2-week
periodic review for its store inventory. Mean and standard
deviation of weekly sales are 16 and 5 respectively. The
lead time is 3 days. The mean and standard deviation of
lead-time demand are 8 and 3.5 respectively.
A. What is the mean and standard deviation of demand
during the review period plus the lead-time period?
B. Assuming that the demand has a normal probability
distribution, what is the replenishment level that will
provide an expected stockout rate of one per year?
C. If there are 18 notebooks in the inventory, how many
notebooks should be ordered?

58
Example 9: Foster Drugs, Inc., handles a variety of health
and beauty products. A particular hair conditioner product
costs Foster Drugs $2.95 per unit. The annual holding cost
rate is 20%. A fixed-quantity model recommends an order
quantity of 300 units per order.
a. Lead time is one week and the lead-time demand is
normally distributed with a mean of 150 units and a
standard deviation of 40 units. What is the reorder point if
the firm is willing to tolerate a 1% chance of stockout on
any one cycle?
b. What safety stock and annual safety stock cost are
associated with your recommendation in part (a)?
c. The fixed-quantity model requires a continuous-review
system. Management is considering making a transition to
a fixed-period system in an attempt to coordinate ordering
59
 for many of its products. The demand during the proposed
two-week review period and the one-week lead-time period is
normally distributed with a mean of 450 units and a standard
deviation of 70 units. What is the recommended
replenishment level for this periodic-review system if the firm
is willing to tolerate the same 1% chance of stockout
associated with any replenishment decision?
d. What safety stock and annual safety stock cost are
associated with your recommendation in part ( c )?
e. Compare your answers to parts (b) and (d). The company is
seriously considering the fixed-period system. Would you
support the decision? Explain.
f. Would you tend to favor the continuous-review system for
more expensive items? For example, assume that the product
in the above example sold for $295 per unit. Explain.
60
Text Problem 5, Chapter 15: Charlie’s Pizza orders all of its
pepperoni, olives, anchovies, and mozzarella cheese to be
shipped directly from Italy. An American distributor stops by
every four weeks to take orders. Because the orders are
shipped directly from Italy, they take three weeks to arrive.

Charlie’s Pizza uses an average of 150 pounds of pepperoni

each week, with a standard deviation of 30 pounds.
Charlie’s prides itself on offering only the best-quality
ingredients and a high level of service, so it wants to ensure
a 98 percent probability of not stocking out on pepperoni.

Assume that the sales representative just walked in the door

and there are currently 500 pounds of pepperoni in the walk-
in cooler. How many pounds of pepperoni would you order?
61
Text Problem 10, Chapter 15: The annual demand for a
product is 15,600 units. The weekly demand is 300 units
with a standard deviation of 90 units. The cost to place an
order is $31.20, and the time from ordering to receipt is
four weeks. The annual inventory carrying cost is $0.10 per
unit. Find the reorder point necessary to provide a 98
percent service probability.

Suppose the production manager is asked to reduce the

safety stock of this item by 50 percent. If she does so, what
will the new service probability be?

62
 Reading and Exercises

• Chapter 15 pp. 586-609

• Exercises:
Chapter end problems 4,5,6,10,12,14 and 20
Examples 5, 8 and 9

63