Chapter 6: Perishable Items

¨Characteristics
¨Simplest Case: the unconstrained, single-item,
newsvendor problem
¨Single-period, Constrained, Multi-item Situation
 1. Characteristics of style goods and
perishable items
 A relatively short selling season.
 There might be one or some chances for replenishment after the initial order is
placed.
 When the demand in the season exceeds the stock made available, there are
associated underage costs.
 When the demand in the season is less than the stock, overage costs result. The
value of items is reduced at a particular point in time.
 Style goods products are often substitutable.
 Sales of style goods are usually influenced by promotion activities and space
allocation in the store.
 One-Time Decision
¨ Situation is common to retail and manufacturing environment

¨ Consider seasonal goods, which are in demand during short period only.
Product 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 “newsvendor” model
Christmas ornament retailer or
Christmas tree
“Christmas tree” model
finished good inventory

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

demand is described as random variable (stochastic case).

3
2. Simplest case: the unconstrained, single
item, newsvendor problem
• 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 in the overage and underage
costs.
• Overage, co: Expected overage cost = co P(X < Q)= G(Q)co

• Underage, cu:Expected shortage cost =cu [1 – P(X < Q)]= (1-G(Q))cu

• For order Q* those two costs are equal: G(Q*)co = (1-G(Q*))cu
Then, probability of satisfying demand during the period, also is
known as critical ratio.
• Decision: Choose Q* satisfies:
 A. Simplest case: Continuous Dist.
• If: X = demand
• v = acquisition cost ($/unit)
• p = revenue per sale ($/unit)
• B = penalty for not satisfying demand ($/unit)
• g = salvage value ($/unit)
Þ Expected profit: 𝐸 [ 𝑃 ( 𝑄 ) ] =( 𝑝−𝑔 ) ⋅ 𝑥
¯ − ( 𝑣−𝑔 ) 𝑄− ( 𝑝 −𝑔+ 𝐵 ) 𝐸𝑆
Þ Choose Q* satisfies:

Normal case: 
N x , x
2
 ∗
𝑄 =𝑥
¯ + 𝑧 𝑝 − 𝑣+ 𝐵 ⋅ 𝜎 𝑥
𝑝 − 𝑔+ 𝐵
Example
 Solution

= 0.712  z = NORMSINV(0.712) = 0.56

 Practice
¨ At the start of each day, a newsvendor must decide on the number of papers
to purchase. Daily sales cannot be predicted exactly and are represented by
the random variable D with normal distribution N(μ, σ), where μ = 11.73 and
σ = 4.74
¨ It can be shown that the optimal number of papers to purchase is given
by F(Q*) = cu / (cu + co),
where cu = 75 – 25 = 50, and c0 = 25 – 10 =15
unrealized profit per unit = (selling price – purchase price);
loss per excess = (purchase price – disposal price);

F(Q*) = cu / (cu + co) = 0.77  Pr ( X < Q* ) = 0.77

¨ How to find Q* ?

8
 Solution
Using NORMSINV to find z = 0.74,
with μ = 11.73 and σ = 4.74

Newsvendor has to
order 15 copies
every week.

9
 B. Simplest Case: Discrete Distribution
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, Probability Solution:
X g(X) Q – order quantity; Q* - optimal
22 0.05 X – demand: random variable with
24 0.10 probability density function g(x)
G(x) – cumulative probability function:
26 0.15
G(x) = Pr (demand ≤ x)
28 0.20 co – cost per unit of positive inventory
30 0.20 cu – cost per unit of unsatisfied demand
32 0.15
34 0.10 Economics marginal analysis:
36 0.05 overage and underage costs are balanced
10
 Example: Mrs. Kandell
Demand Probabilit Cum Mrs. Kandell estimates that
x y g(x) Probability if she buys more trees than
G(x) she can sell, it costs about
22 0.05 0.05 $40 for the tree and its
24 0.10 0.15 disposal. If demand is
26 0.15 0.30 higher than the number of
28 0.20 0.50 trees she orders, she looses
30 0.20 0.70 a profit of $40 per tree.
32 0.15 0.85
34 0.10 0.95
36 0.05 1.00

Q   28

11
 Critical fractile for the newsvendor problem

¨When the demand is a discrete random variable, the

condition G(Q) = cu
cu + co
may not be satisfied at equality (jumps, due to
discreteness). Here’s the appropriate condition to
use: cu
Q = min{Q : PX £ (Q) ³
*
}
cu + co

C(Q+1)-C(Q)=(cu+ co)PX(Q) – cu ≥ 0

12
 Example: Lively Lobsters
¨ Lively Lobsters (L.L.) receives a supply of fresh, live lobsters
from Maine every day. Lively earns a profit of $7.50 for every
lobster sold, but a day-old lobster is worth only $8.50. Each
lobster costs L.L. $14.50
¨ unit cost of a L.L. stockout
Cu = 7.50 = lost profit
¨ unit cost of having a left-over lobster
Co = 14.50 - 8.50 = cost – salvage value = 6
¨ target L.L. service level
CR = Cu/(Cu + Co) = 7.5 / (7.5 + 6) = .56

¨ Demand follows a discrete (relative frequency) distribution as

given on next page

13
 cu
Lively Lobsters Q * = min{Q : PX £ (Q ) ³
cu + co
}

Probability that demand

Demand follows a Cumulative will be less than or equal to x
discrete (relative
Relative Relative
frequency)
distribution: Frequency Frequency
Demand (pmf) (cdf)
Result: 19 0.05 0.05 P(D < 19 )

20 0.05 0.10 P(D < 20 )

order 25 Lobsters,
because that is the 21 0.08 0.18 P(D < 21 )

smallest amount 22 0.08 0.26 P(D < 22 )

that will serve at 23 0.13 0.39 P(D < 23 )
least 56% of the 24 0.14 0.53 P(D < 24 )
demand on a
25 0.10 0.63 P(D < 25 )
56%
given night.
26 0.12 0.75 P(D < 26 )

27 0.10 … P(D < 27 )

28 0.10 … P(D < 28 )

29 0.05
14 … P(D < 29 )

* pmf = prob. mass function

3. Single-period, constrained, multi-
item situation
 Single-period, constrained, multi-
item situation
¨Notation:
¨ n = number of different items (SKUs)
¨ xi = demand of item i.

¨ vi = acquisition cost of item i.

¨ pi = selling price of item i.

¨ Bi = penalty for not satisfying demand of item i.

¨ gi = salvage value of item i.

 Single-period, constrained, multi-
item situation
¨ Step 1: Select an initial positive value of the Lagrange multiplier, M.

¨ Step 2: Determine each Qi to satisfy:

pi  M  1vi  Bi
Pr  X i  Qi   Qi  0 
pi  g i  Bi
n

¨ Step 3: Compare: Q v
i 1
i i vs. W
n

¨ If Q v
i 1
i i W
finish.
n

¨ If Q v  W i i return to step 2 with smaller M.

ni 1

¨ If Q v  W
i 1
i i return to step 2 with larger M
 Example
¨Suppose the Ski Bum was faced with decisions
on 4 items. The manager accepts that in each
case total demand is normal distribution. The
relevant parameter values are estimated in the
following table. The manager has a budget of
$70,000 to allocate among these 4 items.
Solution

>70,000

>70,000

<70,000

70k
 Practice

¨Mr.Lock has to order 2 items with a budget of

$50,000. Characteristics of two items are

¨Assume penalty of stockout is 0.

¨What should Mr.Lock to order?