Supply Chain Management

Part 4 Inventory Management

Speaker: prof. Giuseppe Aiello

Dipartimento di Ingegneria Chimica, Informatica Gestionale Meccanica
(DICGIM)
Universit di Palermo Viale delle Scienze 90128 Palermo (Italy)
[email protected]

Inventory Models
Deterministic models
The Economic Order Quantity (EOQ) model
Probabilistic Inventory models
Single-period inventory models
A fixed order quantity model
A fixed time period model

Inventory Models
The study of inventory models is
concerned with two basic
questions:
How much should be ordered each
time
When should the reordering occur

The objective is to minimize total

variable cost over a specified time
period (assumed to be annual in

Timing Decisions
Quantity decisions made together with decision
When to order?
One of the major decisions in management of the inventory
systems.

Impacts: inventory levels, inventory costs, level of service

provided

Models:
One time decisions
Continuous review systems
Periodic review systems

Timing Decisions

One-Time
Decisions

Continuous Decisions
Continuous Review
System

Intermittent-Time
Decisions
Periodic Review
Systems

EOQ, EPQ

EOQ

(s, Q) System

(S, T) System

Base Stock

(s, S) System

Two Bins

Optional
Replenishment

Inventory Costs
Ordering cost -- salaries and expenses of processing
an order, regardless of the order quantity
Holding cost -- usually a percentage of the value of
the item assessed for keeping an item in inventory
(including finance costs, insurance, security costs,
taxes, warehouse overhead, and other related
variable expenses)
Backorder cost -- costs associated with being out of
stock when an item is demanded (including lost
goodwill)
Purchase cost -- the actual price of the items
Other costs

THE EOQ MODEL

Assumptions
Demand is constant throughout the
year at D items per year.
Ordering cost is $Co per order.
Holding cost is $Ch per item in
inventory per year.
Purchase cost per unit is constant (no
quantity discount).
Delivery time (lead time) is constant.

THE EOQ MODEL

Demand
rate
Inventory Level

Order qty, Q

Reorder point, R
0

Lead
time
Order
Order
Placed
Received

Lead
time
Order
Placed

Time
Order
Received

The EOQ Model Cost

Curves
Annual
cost ($)

Slope = 0
Total Cost

Minimum
total cost

Holding Cost = HQ/2

Ordering Cost = SD/Q
Optimal order Q*

Order Quantity, Q

EOQ Cost Model

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

2 DS
Q
H
*

Probabilistic Inventory
Models
In many cases demand (or some other
factor) is not known with a high degree
of certainty and a probabilistic inventory
model should actually be used.
These models tend to be more complex
than deterministic models.
The probabilistic models covered in this
chapter are:
single-period order quantity
Multi period order quantity

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 multiperiod models, there remains only one question to
answer: how much to order.

Single Period order

quantity mdoel
A single-period order quantity model (sometimes
called the newsboy problem) deals with a
situation in which only one order is placed for
the item and the demand is probabilistic.
If the period's demand exceeds the order
quantity, the demand is not backordered and
revenue (profit) will be lost.
If demand is less than the order quantity, the
surplus stock is sold at the end of the period
(usually for less than the original purchase
price).

One-Time Decision
Situation is common to retail and manufacturing environment
Consider seasonal goods, which are in demand during short period only.
roduct losses its value at the end of the season. The lead time can be
longer than the selling season if demand is higher than the original
order, can not rush order for additional products.

Example
newspaper stand
Christmas ornament retailer
Christmas tree
finished good inventory

newsvendor model
or
Christmas tree model

Trivial problem if demand is known (deterministic case), in practical

situations demand is described as random variable (stochastic case).

Example: One-Time
Decision
Mrs. Kandell has been in the Christmas tree business for
years. She keeps track of sales volume each year and has
made a table of the demand for the Christmas trees and its
probability (frequency histogram).
Demand,
D

Probability
f(D)

22

0.05

24

0.10

26

0.15

28

0.20

30

0.20

32

0.15

34

0.10

36

0.05

Solution:
Q order quantity; Q* - optimal
D demand: random variable with
probability density function f(D)
F(D) cumulative probability function:
F(D) = Pr (demand D)
co cost per unit of positive inventory
cu cost per unit of unsatisfied demand
Economics marginal analysis:
overage and underage costs are balanced

Marginal Analysis
finding the expected profit of
ordering one more unit.
Probability of not selling
Your Last item in stock and having
extra inventory on hand at the end
on the period
P(X < Q)

Probability of
Selling everything, and
facing shortage
P(X Q)

Critical ratio for the

newsvendor problem
P(X<Q)
(Co applies)

P(X>Q)
(Cu applies)

Single Period Inventory Model Marginal Analysis:

E (revenue on last sale) =

E (loss on last sale)

Example: One-Time
Decision (cont)
Shortages = lost profit + lost of goodwill
Overage = unit cost + cost of disposal of the
overage
Either ignore the purchase cost, because it
does not impact the optimal solution or
implicitly
consider
it inQthe
*
Expected
overage
cost of the order
is overage and
underage
P(Demand <costs.
Q*) co = F(Q*)co
Expected shortage cost is
P(Demand > Q*) cu = (1-F(Q*)) cu
For order Q* those two costs are equal: F(Q*)co = (1-F(Q*))cu

cu
P DQ F Q
cu co of satisfying demand during
- probability

the period, also is known as critical ratio

Optimal Q

Cost of overstocking by one unit = Co

the out-of-pocket cost per unit stocked but not demanded
Say demand is one unit below my stock level. How much did the
one unit overstocking cost me?
E.g.: purchase price - salvage
price.

Cost of understocking by one unit = Cu

The opportunity cost per unit demanded in excess of the stock level
provided
Say demand is one unit above my stock level. How much could I
have saved (or gained) if I had stocked one unit more? E.g.: retail
price - purchase price.

Given an order quantity Q, increase it by one unit if and only if

the expected benefit of being able to sell it exceeds the
expected cost of having that unit left over.
Marginal Analysis: Order more as long as F(Q) < Cu / (Co + Cu)
smallest Q such that service level F(Q) > critical fractile Cu / (Co
+ Cu)

Newsvendor discreet
demand
Demand Probability
f(D)
D

Cum
Probability
F(D)

22

0.05

0.05

24

0.10

0.15

26

0.15

0.30

28

0.20

0.50

30

0.20

0.70

32

0.15

0.85

34

0.10

0.95

36

0.05

1.00

cu
40
FQ

0.50
cu co 40 40

Mrs. Kandell estimates that

if she buys more trees than
she can sell, it costs about
$40 for the tree and its
disposal. If demand is
higher than the number of
trees she orders, she looses
a profit of $40 per tree.

Q 28

Another Example: Apparel Industry

How much to order? Parkas at L.L.
Bean

D
eD
m
a
n
d
P
r
o
b
a
b
a
b
i
l
t
y
C
u
m
u
l
a
t
i
v
e
P
r
o
b
a
b
i
l
t
y
o
f
d
e
m
a
n
d
P
r
o
b
a
b
i
l
t
y
o
f
d
e
m
a
n
d
i4
_
p
_
i
b
e
i
n
g
t
h
i
s
s
i
z
e
o
r
l
e
s
,
F
(
.
)
g
r
e
a
t
e
r
t
h
a
n
h
i
s
s
i
z
e
,
1
F
(
.
)
.
0
1
.
0
1
.
9
5
.
0
2
.
0
3
.
9
7
6
.
0
4
.
0
7
.
9
3
7
.
0
8
.
1
5
.
8
5
8
.
0
9
.
2
4
.
7
6
9
.
1
.
3
5
.
6
5
1
0
.
1
6
.
5
1
.
4
9
1
.
2
0
.
7
1
.
2
9
1
2
.
1
.
8
2
.
1
8
1
3
.
1
0
.
9
2
.
0
8
1
4
.
0
4
.
9
6
.
0
4
1
5
.
0
2
.
9
8
.
0
2
1
6
.
0
1
.
9
.
0
1
17 .01 1.0
.0

Expected demand is 1,026 parkas.

21

Parkas at L.L. Bean

Cost per parka = c = $45
Sale price per parka = p = $100
Discount price per parka = $50
Holding and transportation cost = $10
Salvage value per parka = s = 50-10=$40
Cost of understocking = Profit from selling
parka = p-c = 100-45 = $55
Cost of overstocking = c-s = 45-40 = $5

Optimal Order Size

p = sale price; s = outlet or salvage price; c = purchase price
Raising the order size by one unit:
Expected Marginal Benefit =
=P(Demand is above stock)*(Profit from sales)=F(Q) (p c)
Expected Marginal Cost =
=P(Demand is below stock)*(Loss from discounting)=(1F(Q))(c - s)
Define Co= c-s; Cu=p-c

Order Quantity for a

Single Order
Co = Cost of overstocking = $5
Cu = Cost of understocking = $55
Q* = Optimal order size

Cu
55
P ( Demand Q )

0.917
Cu Co 55 5
*

24

Optimal Order Quantity

0.917

Optimal Order Quantity = 13(00)

Parkas at L.L. Bean

Additional Expected
Expected
Expected Marginal
100s
Marginal Benefit Marginal Cost Contribution
11th
5500.49 = 2695 500.51 = 255 2695-255 = 2440
12th

5500.29 = 1595 500.71 = 355 1595-355 = 1240

13th

5500.18 = 990

500.82 = 410 990-410 = 580

14th

5500.08 = 440

500.92 = 460 440-460 = -20

15th

5500.04 = 220

500.96 = 480 220-480 = -260

16th

5500.02 = 110

500.98 = 490 110-490 = -380

17th

5500.01 = 55

500.99 = 495 55-495 = -440

26

Parkas at L.L. Bean

Suppose LLBean decides to buy
1000 products:
Expected profit:
10

Expected profit Di ( p c) (1000 Di )(c s) pi

i4

(1 Pi )1000( p c)
D i demand, p i corresponding probability

Expceted

profit from ordering 1000 pezzi =$49.900

27

Expected Profit Curve

Units

Expected Profit

600

27440

700

32760

800

37840

900

42400

1000

49900

1100

52340

1200

53580

1300

54160

1400

54140

1500

53880

1600

53500

1700

53060

28

Newsvendor Uniform
distribution
We have a continuous demand
uniformly distributed between 1000
and 7000
Co=20, Cu=5
P(D Q*) Cu / (Co+Cu)
Cu / (Co+Cu) = 20/25 = 0.8
Order until P(D Q*) 0.8

Newsvendor Uniform
distribution
Q-l = Q-1000
?
0.80
l=1000

1/6000
u=7000

u-l=6000
(Q-1000)*1/6000=0.80
Q = 5800

Newsvendor Normal
distribution
Suppose the demand is normally
distributed with a mean of 4000 and
a standard deviation of 1000.
What is the optimal order
quantity?
We only need to find the right value of
Q assuming the normal distribution.

Newsvendor Normal
distribution
0.00045
0.0004
0.00035

Probability of
excess inventory

0.0003
0.00025

Probability of
shortage
4841

Series1

0.0002
0.00015
0.0001
0.80

0.00005
0
0

1000

2000

3000

4000

0.20 6000
5000

7000

8000

Newsvendor Model
Notation
X demand (in units), a random variable.
G ( x) P ( X x), cumulative distribution function of demand
(assumed continuous.)
g ( x)

d
G ( x) density function of demand.
dx

co cost (in dollars) per unit left over after demand is realized.
cs cost (in dollars) per unit of shortage.
Q production/order quantity (in units); this is the decision variable.

The newsvendor model

with continuous demand
Units over = max {Q-X, 0}
Units short = max {X-Q, 0}

Cost Function:
Y (Q ) expected overage cost expected shortage cost
co E units over cs E units short

co max Q x,0 g ( x)dx cs max x Q,0 g ( x)dx

co

(Q x) g ( x)dx 0 g ( x)dx cs 0 g ( x )dx ( x Q) g ( x)dx

Q
Q
Q

co (Q x ) g ( x)dx cs ( x Q ) g ( x)dx
Objective: find the value of Q that minimizes this expected cost.

Newsvendor Model
Leibnitzs rule
For Y(Q): taking its derivative and setting
it to 0.
To do this, we need to take the derivative
of integrals with limits that are functions
Leibnitz's darule
can do da (Q)
a ( Q ) Q. A tool
a ( Q ) called
d of

2 (Q )
1
f
(
x
,
Q
)
dx

[
f
(
x
,
Q
)]
dx

f
(
a
(
Q
),
Q
)

f
(
a
(
Q
),
Q
)
2
1
a (Q) Q
(Q )
dQ athis.
dQ
dQ
2

Applying this for Y(Q):

dY (Q)
c0
dQ

1g ( x) dx c s

(1) g ( x)dx c G(Q) c [1 G(Q)] 0

Q

cs
G (Q )
co c s
*

Newsvendor model
D(,)=one period random demand
c=unit cost, p>c=selling price s<c=salvage value,

if Q uints are ordered:

min(Q,D) = units sold
max (Q-D,0)= = units salvaged.

The expected profit is defined as:

Being: min(Q,D)=D-(D-Q)+

This Equation allows to view the problem of maximizing (Q) as that

of minimizing the expected overage and underage cost G(Q).
Define Co= c-s; Cu=p-c

Newsvendor expected
cost

Newsvendor model

Inventory policy
performance (Availability)
measures
Expected lost sales
The average number of units demand exceeds the order
quantity

Expected sales
The average number of units sold.

Expected left over inventory

The average number of units left over at the end of the season.

Expected profit
Expected fill rate
The fraction of demand that is satisfied immediately

In-stock probability
Probability all demand is satisfied

Stockout probability
Probability some demand is lost

expected units sold

the expected number of units sold is:

where

Expected lost sales

=
w

For normally
distributed demand

It is also:

Expected number of units

salvaged (inventory at the
end of the season)

For Normally distributed demand:

Expected profit

Expected profit
normally distributed demand
For

Relationships between
expected values

In other words, for any order quantity Q, the expected profit is the
profit for selling the average demand, ( p - c) , less the expected
cost. The expected cost, therefore, can be interpreted as the cost of
demand variability and the organization should be willing to pay
that amount to reduce uncertainty to zero.

Example
Hotel/Airline Overbooking
The forecast for the number of
customers that DO NOT SHOW
UP at a hotel with 118 rooms is
Normally Dist with mean of 10
and standard deviation of 5
Rooms sell for $159 per night
The cost of denying a room to
the customer with a confirmed
reservation is $350 in ill-will and
penalties.
Let X be number of people who
do not show up X follows a
probability distribution!
How many rooms ( Y ) should be
overbooked (sold in excess of
capacity)?

Newsvendor setup:
Single decision when the
number of no-shows in
uncertain.
Underage cost if X > Y
(insufficient number of
rooms overbooked).
For example, overbook 10
rooms and 15 people do not
show up lose revenue on 5
rooms

Overage cost if X < Y (too

many rooms overbooked).
Overbook 10 rooms and 5 do
not show up; pay penalty on 5
rooms

Overbooking solution
Underage cost:
if X > Y then we could have sold X-Y more rooms
to be conservative, we could have sold those rooms at the
low rate, Cu = rL = $159

Overage cost:
if X < Y then we bumped Y - X customers
and incur an overage cost Co = $350 on each bumped
customer.

Optimal overbooking level:

Critical ratio:

F (Y )

Cu
.
Co Cu

Cu
159

0.3124
Cu Co 350 159

Optimal overbooking level

Suppose distribution of no-shows is normally

distributed with a mean of 10 and standard deviation of
5
Critical ratio is:
Cu
159

0.3124
Cu Co 350 159

z = NORMSINV(.3124) = -0.4891
Y = + z = 10 -.4891 * 5 = 7.6
Overbook by 7.6 or 8

Hotel should allow up to 118+8 reservations.

Multi period Inventory

control policies

Shortage and Demand in a

Cycle

Quantity

Demand During Lead Time & Safety

stock
Maximum probable demand
during lead time
Expected demand
during lead time

ROP
Safety stock
LT

Time

DLT : Demand during lead time

LT and demand may be uncertain
D Average demand per period

D2 Variance of demand
L Average lead time in number of periods
2
LT
Variance of lead time

Expected value of the demand during lead time

LT

E ( Di ) ( L)( D)
i 1

Variance of the demand during lead time

LT

2
2
Var ( Di ) L D D 2 LT
DLT
i 1

Expected shortage per

cycle
ESC is the expected shortage in a Cycle
ESC is not a percentage, it is the number of
units
DLT - ROP if
Shortage
0
if

DLT ROP
DLT ROP

ESC E(max{Demand during leadtime ROP,0})

ESC

(x - ROP)f(x)dx

x ROP

f (x) is density function of demand distribution during the lead time

Expected shortage during a

Cycle
Expected shortage E (max{D ROP,0})

( D ROP) f

( D)dD where f D is pdf of D.

D Q

d1 9 with prob p1 1/4

ROP 10, D d 2 10 with prob p2 2/4 , Expected Shortage?

d 11 with prob p 1/4
3
3

Expected shortage max{0, ( d i ROP )} pi

i 1

11

(d ROP)}P( D d )

d 10

1
2
1 1
max{0, (9 - 10)} max{0, (10 - 10)} max{0, (11 - 10)}
4
4
4 4

Expected shortage per cycle

ROP 10, D Uniform(6,12), Expected Shortage?
D 12

1 10 2

1
1 D2
1 12 2
Expected shortage ( D 10) dD
10 D

10(12)
10(10)
6
6 2
6 2
6 2

D 10
D 10
172 - 170 2
12

If demand is normal:

ESC ss 1 normdist

ss

,0,11
, L normdist

Does ESC decrease or increase with ss, L?

Does ESC decrease or increase with expected value of
demand?

ss

,0,1,0

Multi period Inventory

control policies

Controllo Periodico

Controllo Continuo (R=0)

(punto di riordino: s)

Lotto di dimensione Fissa

(R,Q)

(s,Q)

A raggiungimento
dellOrder up to level S o
L

(R,S)

(s,S)

(s,Q) system Continuous

Review

if inventory position <= s,

then order Q

(s, S) system Continuous

Review

If inventory position <= s,

order up to S = s+Q

(R, S) system Periodic

Review

Every R units of time, order

up to S

(R, s, S) system Periodic

Review

Every R units of time, check

position. If less
than s, then order up to S.

Terminology
On-hand stock: Stock that is physically on the shelf
Net stock = On-hand stock Backorders
Committed stock =stock that cannot be used in the
short run and it is dedicated to other purposes
Inventory Position =
On-hand + On-order (Backorders Committed)
Complete backordering: backordered demand is filled
as soon as an adequate-size replenishment arrives
Complete lost sales: when out of stock, demand is
lost, customers go somewhere else

Multi period Inventory

control policies
Continuous Review Systems
(s, Q) Policy: Whenever the inventory position (items on hand plus
items on order) drops to a given level s or below, an order is placed for a
fixed quantity Q.
(s, S) Policy: Whenever the inventory position (items on hand plus
items on order) drops to a given level s or below, an order is placed for a
sufficient quantity to bring the inventory position up to a given level S.
Periodic Review Systems
(T, S) Policy: Inventory position (items on hand plus items on order) is
reviewed at regular instants, spaced at time intervals of length T. At each
review, an order is placed for a sufficient quantity to bring the inventory
position up to a given level S.
(T, s, S) Policy: Inventory position (items on hand plus items on order)
is reviewed at regular instants, spaced at time intervals of length T. At
each review, if inventory position is at level s or below, an order is placed
for a sufficient quantity to bring inventory position up to a given level S; if
inventory position is above s, no order is placed. This policy is also known
as a periodic review (s, S) policy.

Continuous Review Policies

Controllo Continuo (R=0) (punto di riordino: s)

Lotto di
dimensione
Fissa

(s,Q)

A
raggiungimento
dellOrder up to
level S o L

(s,S)

(s, Q) (order point, order quantity) Continuous Review o stocastic EOQ

The ( s, Q) inventory policy (reorder point, order quantity
system) assumes that the inventory level is observed at all
times (continuous review) When the level declines to some
specified Reorder point, s , an order is placed for a lot size Q .
The order arrives to replenish the inventory after a lead time, L

The random demand during the lead time gives rise to the
possibility that the inventory level will be depleted before the
replenishment arrives.

Safety Stock
shortage will occur if the demand
A
during the period L is greater than s
The service level is the probability that
the inventory will not be depleted
during one order cycle:
The safety stock, SS is: SS=s-

Nomenclature

Ordering cost (c(z)): Costo di Lancio Ordine

Setup cost (K): costo di lancio ordine
Product cost (c): costo unitario del prodotto
Holding cost (h): costo di mantenimento a scorta generalmente ottenibile
come prodotto di c per un tasso di interesse (/pz/tempo).
Shortage cost (Cs): Costo cui si va incontro quando un cliente non trova il
prodotto disponibile e la domanda va persa o soddisfatta non appena il
prodotto di nuovo disponibile (backorder). Nel caso pi generale il costo
totale di backorder proporzionale alla quantit non soddisfatta ed al
tempo di attesa del cliente. (/pz/tempo)
Annual Demand rate (a): tasso di domanda (pz / Anno)
Lot Size (Q): dimensione del lotto (pz)
Order level (S): Il livello di scorta Massimo raggiunto dalla scorta in
magazzino. Pari a Q se sono consentiti i backorders, minore di Q se i
backorder non sono consentiti.
Cycle time: Tempo che intercorre tra due cicli di approvvigionamento del
magazzino, pari a Q/a (tempo)

Optimal Solution (s, Q)

Policy
(backlogged demand)
L
Average demand during the lead
time : =aL

General Solution

a general expression for the optimum lot size
that depends on the cost due to shortages

The solution for the optimum reorder point

depends on the functional form of the cost of
shortage

Backorder case -Fixed Cost

per Stockout

Backorder case -Fixed Cost

per unit short

penalty cost per unit short.

The Lost Sales Case

=penalty

cost per unit Lost

Solution Procedure
The optimal solution procedure requires
iterating between the two equations for Q
and R until convergence occurs
A cost effective approximation is to set
Q=EOQ and find R from the second
equation.

Finding Q and s,
iteratively
1. Compute Q = EOQ.
2. Compute s.

3. Use R to compute Es.

4. Solve for Q in Equation (1).

5. Go back to Step 2, continue until convergence.

Example
A company purchases air filters at a rate of 800 per
year
10 to place an order
Unit cost is 25 per filter
Inventory carry cost is 2/unit per year
Shortage cost is 5 per product
Lead time is 2 weeks
Assume demand during lead time follows a uniform
distribution from 0 to 200
Find (Q,R)

Solution
Partial

derivative outcomes:

Solution
From

Uniform U(0,200) distribution:

1
1
U(0,200) : f ( x)

b - a 200

200

ESC n( s) ( x s ) f ( x)dx
1 x 2

sx
200 2

s2
100
s
400

x 200

xs

1
( x s)
dx
200

2
2

1
200
s
2

200 s s
200 2
2

s2
n(s)
s 100
400
Q1 8000 4000n(s)

Solution
Iteration

Q
1 F (s)
2000

1:

2K
2(10)(800)
EOQ

8000 89.44 Qo
h
2
F(s)
Qo h
89
1 F ( so )

.04
a 2 2000
F ( so ) .96
s o (.96)(200 0) 192

200
s

s2
n(s)
s 100
400
Q1 8000 4000n(s)

Solution
Iteration

2:

Q
1 F (s)
2000

(192) 2
n ( s0 )
192 100 .198
400
Q1 8000 4000(.198) 93.76
94
1 F ( s1 )
.05
2000
s1 (.95)( 200) 190

R2
n( R )
R 100
400
Q1 8000 4000n(R )

Solution
Iteration

3:

1 F ( R)

190
n( s1 )
190 100 .2197
400
Q2 8000 4000(.2197) 94.228
94
(1 F ( s2 ))
.05
2000
s2 190

Q
2000

Solution
R

didnt change => CONVERGENCE

(Q*,s*) = (94,190)
I(t)
253
190

159

Slope

Withleadtimeequalto2weeks:
SS=R=190800(2/52)=159

Example
Demand is Normally distributed with mean of 40 per
week and a weekly variance of 8
The ordering cost is $50
Lead time is two weeks
Shortages cost an estimated $5 per unit short to
expedite orders to appease customers
The holding cost is $0.0225 per week
Find (Q,R)

Solution

N (40,2 2 )
Demand is
per week.
Lead time is two weeks long. Thus, during the
lead time:
Mean demand is 2(40) = 80
Variance is (2*8) = 16
Demand observed in one week is independent
from demand observed in any other week:
E(demand over 2 weeks) = E (2*demand over
week 1)
= 2 E(demand in a single week) = 2 = 80

Standard deviation over 2 weeks is =

Finding Q and s, iteratively

1. Compute Q = EOQ.
2. Substitute Q and compute s.
Qh
1 F (s)
p
3. Use s to compute average backorder level, n(s).

n( s ) ( x s ) f ( x)dx
s

4. Solve for Q using:

2 K p n(s)
Q
h
5. Go to Step 2 until convergence.

Solution

Iteration 1:
2K
2(50)(40)
EOQ

421.6 Qo
h
.0225
Qo h 421.6(.0225)
1 F ( so )

.0473
a 2
5(40)

F ( so ) .9527

From the standard normal table:

)=.9527
P(z1.67)=0.9527
=+Z=80+1.67

Normal Loss Function

If X is normally distributed, the determination of
ESC requires a knowledge of the normal loss
function.

=standardized normal density

It can be shown that:

Solution
Iteration

2:

This is the unit normal loss

expression.

Solution
Iteration

2:

n( s0 ) .0788
2 K pn( R)
2(40) 50 5(.0788)
Q1

423.3
h
.0225
Q1h 423.3(.0225)
1 F ( s1 )

.0476
p
5(40)
F ( s1 ) .9523
s1 86.68
Convergence!