Professional Documents
Culture Documents
ti
David Simchi-Levi
Sources
Dt qt
Retailer Manufacturer
L
A Simple Supply Chain:
O d off Event
Order E ts
z At end of period t:
)Retailer updates forecast based on Dt.
)Calculates
Calculates order
order-up-to
up to point, yt+1.
)Places order qt+1.
)O d arrives
)Order i t t off period
att start i d t+L.
t+L
)Demand is observed and filled.
)Unfilled demand is backlogged.
A Simple Supply Chain:
I
Inventory
t Policy
li
y t = L μ$ t + z LS t
A Simple Supply Chain:
M i A
Moving Average Forecast
p p
∑ Dt−i ∑ ( Dt−i − μ$ t )
2
$μ t = i=1 St = i=1
p p −1
Moving Average Forecasting:
Od Q
Order Quantity
tit
qt = yt − yt−1 + Dt−1
⎛ L⎞ ⎛ L ⎞
⎞
= ⎜ 1+ ⎟ Dt−1 − ⎜ ⎟ Dt− p−1 + z L( S t − S t−1 )
⎝ p⎠ ⎝ p⎠
Moving Average Forecasting:
Th V
The Variability
i bilit off Orders
Od
⎛ 2L 2L ⎞ 22
Var( qt ) = ⎜ 1+ + 2 ⎟ σ + z LVar( St − St −1 )
2
⎝ p p ⎠
⎛ 2L⎞
+2z L⎜ 1+ ⎟ Cov( Dt−1 ,St ).
⎝ p⎠
Moving Average Forecasting:
Symmettriic Demand
d
is:
Var (qt
) 2L 2L2 + z 2 L
≥1+ + .
σ2 p p 2
Var(q)/σ :
2
L B d vs. Si
Lower Bound l ti
Simulation
3
25
2.5
1.5
0.5
0
0 10 20 30 40
p
Bound Simulation
Var(q)/σ :
2
F V i
For Various L d Ti
Lead Times
14
L=5
12
10
8 L=3
6
4 L=1
L=1
2
0
0 5 10 15 20 25 30
The Bullwhip Effect:
Manageriiall Insi
I ights
ht
L2
Multi-Stage Supply Chain:
C t lized
Centrali d IInfformation
ti
At the end of period t-1, stage i:
)Receives order qii-11
t.
)Receives updated forecast from retailer.
)Orders qit.
C t lized
Centrali d IInfformation
ti
C t lized
Centrali d IInfformation
ti
Lemma: When the retailer uses a moving average
with p observations,
observations the increase in variability at
at
stage k is:
2
⎡∑ L ⎤ 2 ⎡∑ L ⎤
k k
Var ( q )
k 2
⎢⎣i=1 i ⎥⎦ ⎢⎣i=1 i ⎥⎦
=1+ +
σ 2
p p
f ti
z The retailer does not provide upstream
p −1
i
−1
∑q t −
j
j =
0
μ
$ =
i
t
i
=
Li
μ$ i
t
p
f ti
with
i h p observations,
b i the
h increase
i in
i variability
i bili
at
stage k is:
Var ( q k
) ≥ ∏ ⎡1 + 2 L
k 2 Li ⎤
2
⎢
i
+ 2 ⎥
σ 2
i=1 ⎣ p p ⎦
The Bullwhip Effect:
Manageriiall Insi
I ights
ht
z Exists, in part, due to the retailer’s need to estimate
the mean and variance of demand
demand.
z The increase in variability is an increasing function of
the lead time and the smoothing g parameter.
)With longer lead time need more demand data
to reduce the bullwhip effect.
z The more complicated the demand models and the
forecasting techniques, the greater the increase.
z Centralized demand information can reduce the
bullwhip effect, but will not eliminate it.
MIT OpenCourseWare
http://ocw.mit.edu
For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.