Global Supply Chain Network Design

under Uncertainty

MGO 636 Supply Chain Analytics 1

 Outline
• Impact of Uncertainty
• Discounted Cash Flow Analysis
• Representations of Uncertainty
• Decision Trees

MGO 636 Supply Chain Analytics 2

 Exchange Rate Uncertainty

MGO 636 Supply Chain Analytics 3

 Price Uncertainty
Crude Oil and Natural Gas Prices

MGO 636 Supply Chain Analytics 4

 Interest Rate Uncertainty
US Federal Funds Rate

MGO 636 Supply Chain Analytics 5

 Demand Uncertainty

MGO 636 Supply Chain Analytics 6

 Impact of Uncertainty
• There will be a good deal of uncertainty in
demand, prices, exchange rates, and the
competitive market over the lifetime of a
supply chain network.
• Network design decisions include
investments in number and size of plants,
number of trucks, number and size of
warehouses, etc.
• These decisions cannot be easily changed
in the short-term.
MGO 636 Supply Chain Analytics 7
 Outline
• Impact of Uncertainty
• Discounted Cash Flow Analysis
• Representations of Uncertainty
• Decision Trees

MGO 636 Supply Chain Analytics 8

 Discounted Cash Flow Analysis

• Supply chain network design decisions are

in place for a long time, so they should be
evaluated as a sequence of cash flows
over that period.
• Discounted cash flow (DCF) analysis
evaluates the present value of any stream
of future cash flows.
• Based on the time value of money – a
dollar today is worth more than a dollar
tomorrow.
MGO 636 Supply Chain Analytics 9
 Discounted Cash Flow Analysis
• Compare Net Present Value (NPV) of different
supply chain design options.
• If $1 today can be invested and earn a rate of
return k over the next period, then
$1 today = $(1+k) in the next period, or
$1/(1+k) today = $1 in the next period
• Discount factor = 1/(1+k)
t
 1 
T
NPV  C0     Ct
t 1  1  k 

where
C0 , C1 ,..., CT is a stream of cash flows over T periods
MGO 636 Supply Chain Analytics 10
 NPV Example: Trips Logistics
• A logistics firm that provides warehousing
services
– Annual demand = 100,000 units
– Requires 1,000 sq. ft. of space for every 1,000 units of
demand
– Revenue = $1.22 per unit of demand
• Decision is whether to sign a three-year lease
or obtain warehousing space on the spot
market
– Three-year lease cost = $1 per sq. ft. per year
– Spot market cost = $1.20 per sq. ft. per year
– Rate of return k = 0.1
MGO 636 Supply Chain Analytics 11
 NPV of Leasing on Spot Market
• For leasing warehouse space on the spot market:
Expected annual profit = 100,000$1.22
– 100,000$1.20 = $2,000
• Annual Cash flow = $2,000
• Total Cash flow = $6,000 in the next three years?
[Yes or No?]
• Discount factor = 1/(1+k) = 1/1.1  0.91
NPV = C0 + C1/(1+k) + C2/(1+k)2
= 2000 + 2000(0.91) + 2000(0.91)2 = $5,471

MGO 636 Supply Chain Analytics 12

 NPV of the Three-Year Lease
• For leasing warehouse space with a three-year lease:
Expected annual profit = 100,000$1.22
– 100,000 $1.00 = $22,000
• Cash flow = $22,000 in each of the next three years
NPV = C0 + C1/(1+k) + C2/(1+k)2
= 22000 + 22000(0.91) + 22000(0.91)2 = $60,182

• The NPV of signing the lease is $54,711 (10+ times)

higher.
• However, uncertainty in demand and costs may
cause the manager to rethink his decision.
MGO 636 Supply Chain Analytics 13
 Outline
• Impact of Uncertainty
• Discounted Cash Flow Analysis
• Representations of Uncertainty
• Decision Trees

MGO 636 Supply Chain Analytics 14

 Binomial Representations
• When moving from one period to the
next, the value of the underlying factor
(e.g., demand or price) has only two
possible outcomes – up or down

MGO 636 Supply Chain Analytics 15

 Multiplicative Binomial Representation
• The underlying factor moves up by a factor u > 1 with
probability p, or down by a factor d < 1 with probability
1-p

• Assuming a price P in period 0, for the multiplicative

binomial, the possible outcomes for the next four
periods:
– Period 1: Pu, Pd
– Period 2: Pu2, Pud, Pd2
– Period 3: Pu3, Pu2d, Pud2, Pd3
– Period 4: Pu4, Pu3d, Pu2d2, Pud3, Pd4
• In general, for multiplicative binomial, period T has
all possible outcomes Putd(T-t), for t = 0,1,…,T
MGO 636 Supply Chain Analytics 16
 Additive Binomial Representation
• The underlying factor moves up by u with
probability p, or down by d with probability 1-p.

• Assuming a price P in period 0, for the additive

binomial, the possible outcomes for the next four
periods:
– Period 1: P+u, P-d
– Period 2: P+2u, P+u-d, P-2d
– Period 3: P+3u, P+2u-d, P+u-2d, P-3d
– Period 4: P+4u, P+3u-d, P+2u-2d, P+u-3d, P-4d

• In general, period T has all possible outcomes

P+tu-(T-t)d, for t = 0, 1, …, T
MGO 636 Supply Chain Analytics 17
 Limitation of Binomial Uncertainty
• The underlying factor takes on only one of two
possible values at the end of each period.

• To overcome this limitation, we have to make the

period short enough  increase # of periods.

• As the # of periods increases, the probability

distribution among the end states resemble the
normal distribution. YouTube Video: Ball Drop

• This is a reasonable assumptions for many

factors such as demand, price, or exchange rate.
MGO 636 Supply Chain Analytics 18
 Outline
• Impact of Uncertainty
• Discounted Cash Flow Analysis
• Representations of Uncertainty
• Decision Trees

MGO 636 Supply Chain Analytics 19

 Decision Tree

MGO 636 Supply Chain Analytics 20

 Decision Trees
• Many of the network design decisions involve a choice
between a long-term (or less flexible) option and a
short-term (or more flexible) option.

• If uncertainty is ignored, the long-term option will

almost always be selected because it is typically
cheaper.

• Such a decision can eventually hurt the firm, however,

because actual future prices or demand may be
different from what was forecasted at the time of the
decision.

• A decision tree is a graphic device that can be used

to evaluate decisions under uncertainty.
MGO 636 Supply Chain Analytics 21
 Binomial Decision Tree
binomial decision tree
• One way to represent
uncertainty is a
binomial tree.

• For example, a ball

moves up by u = 1 or
down by d = 1 with
equal probability.

T periods

MGO 636 Supply Chain Analytics 22

 Decision Tree Example: Trips Logistics
• Must decide whether to lease warehouse space
for the coming T = 3 years and the quantity to
lease.

• Long-term lease is currently cheaper than the

spot market rate.

• The manager anticipates uncertainty in demand

and spot prices over the next three years.

• Long-term lease is cheaper but could go unused

if demand is lower than forecast; future spot
market prices could also decrease.
MGO 636 Supply Chain Analytics 23
 Trips Logistics: Three Options

• Option 1: Get all warehousing space from the

spot market as needed.

• Option 2: Sign a three-year lease for a fixed

amount of warehouse space

• Option 3: Flexible lease to use between 60,000

and 100,000 sq. ft.

MGO 636 Supply Chain Analytics 24

 Trips Logistics Decision Tree
Period 2
D=144

Period 0 Period 1 0.25 P=$1.45

0.25 D=144
P =$1.19
D=120
P=$1.32 0.25 D=96
0.25 P =$1.45
0.25 D=144
D=120
0.25 P=$1.08
P =$0.97

D=100 D=96
P=$1.20 0.25 P =$1.19

D=80 D=96
P=$1.32 P =$0.97
0.25 D=64
P =$1.45
D=80
P=$1.32 D=64
P =$1.19

D=64
P =$0.97

MGO 636 Supply Chain Analytics 25

 Trips Logistics Results

Option Value
All warehouse space from the spot market $5,471
Lease 100,000 sq. ft. for three years $38,364
Flexible lease to use between 60,000 and 100,000 sq. ft. $46,545

MGO 636 Supply Chain Analytics 26

 Next…

Discussion of Transportation

MGO 636 Supply Chain Analytics 27