Session10 P

Download as pdf or txt
Download as pdf or txt
You are on page 1of 12

Session 10: Inventory Management

Inventory Management of Style


Goods
Single Period Models
(also known as newsvendor problem)
Applications of too much-too little
• Capacity planning
• Inventory management
• Airline overbooking
• Cash reserves for redemptions in mutual fund
• Placements
• Admissions
• Attendance
• Monthly cellphone plan
Single period inventory problem

• Only one ordering opportunity


• Mismatch
– Co: Overstocking cost per unit
– Cu: Understocking cost per unit
• Context
– Demand is uncertain and follows a probability
distribution
– How much to order?
Single period problem
Newsvendor Problem
• Mismatch
– Co: Overstocking cost per unit
– Cu: Understocking cost per unit
– Optimal service Level (SL) is determined by this
critical ratio

$%
!" =
$% &$'

– Service level (probability of not stocking out)


Example of newsvendor trade-offs
• Consider a fashion apparel
– About 6 months before winter production quantities are
determined based on demand forecasts
– One production opportunity
– Based on past sales, knowledge of the industry, and economic
conditions, the marketing department has a probabilistic
forecast
– Overestimating demand leads to unsold inventory
– Underestimating demand leads to lost sales
Demand Forecast

Demand Scenarios

30%
Probability

25%
20%
15%
10%
5%
0%

Sales
Relevant Costs
• Production cost per unit (C): 80

• Selling price per unit (S): 125

• Salvage value per unit (V): 20

• Q is order quantity, D is random variable of demand


Solution
Demand Probability Cum Prob.
8000 0.11 0.11
10000 0.11 0.22
12000 0.27 0.49
14000 0.22 0.71
16000 0.19 0.9
18000 0.1 1

125−80 45
Pr(D ≤ Q) = = = 0.43
125−80 +80 − 20 105
Q =12000
Continuous Distribution
• Let P = 5, C = 1.25
• μ=9000
• σ=2000
• Cu = 3.75
• Co = 1.25
• SL* = (3.75/5) = 0.75
• Z(SL=0.75) = 0.674
• Q = 9000 + (.674)2000 = 10,348
Continuous Distribution
• Let P = 5, C = 3
• μ=9000
• σ=2000
• Cu = 2
• Co = 3
• SL* = (2/5) = 0.4
• Z(SL=0.4) = -0.25
• Q = 9000 – (0.25)2000 = 8,500
Observations
• Why Q < μ
• Expected profit is same for Q = 9000, Q = 16000
– What to chose?

You might also like