Safety Inventories: Chapter 11 of Chopra
Safety Inventories: Chapter 11 of Chopra
Safety Inventories: Chapter 11 of Chopra
Chapter 11 of Chopra
1
utdallas.edu/~metin
Why to hold Safety Inventory?
Desire for product availability
– Ease of search for another supplier
– “I want it now” culture
Demand uncertainty
– Short product life cycles
Safety inventory
2
utdallas.edu/~metin
Measures
Measures of demand uncertainty
– Variance of demand
– Ranges for demand
Delivery Lead Time, L
Measures of product availability
– Stockout?
» Backorder (patient customer, unique product or big cost advantage) or
Lost sales.
– Cycle service level (CSL), % of cycles
– Product fill rate (fr), % of products
– Order fill rate, % of orders
» Equivalent to product fill rate if orders contain one product
3
utdallas.edu/~metin
Service measures: CSL and fr are different
inventory
CSL is 0%, fr is almost 100%
0 time
inventory
CSL is 0%, fr is almost 0%
0 time
4
utdallas.edu/~metin
Replenishment policies
When to reorder?
How much to reorder?
– Most often these decisions are related.
5
utdallas.edu/~metin
Demand During Lead time
Di demand in period i. Mostly Di ∝ Normal ( Ri , σ i2 )
f i , Fi probabilit y density and cumulative density functions for D i
Ri = E ( Di ) = ∫ Di f i ( Di )dDi Var ( Di ) = σ i2 = E{( Di − Ri ) 2 } = ∫ ( Di − Ri ) 2 f i (Di ) dDi
i =1 i =1
frequency
normdist(x,.,.,1) normdist(x,.,.,0)
Prob
95.44%
99.74%
normdist(x,mean,st_dev,1)
0 x
norminv(prob,mean,st_dev)
E ( ∑ D i ) = LR and Var ( ∑ D i ) = L σ
L L
2
i =1 i =1
∑
L
If D i ∝ N ( R , σ ) then
2
D i ∝ N ( LR , L σ 2 )
i =1
Q
ROP
time
Lead Times
Shortage
10
utdallas.edu/~metin
Cycle Service Level
Cycle service level: percentage of cycles with stock out
13
utdallas.edu/~metin
Finding Safety Inventory for given CSL
R = 2,500/week; σ= 500
L = 2 weeks; Q = 10,000; CSL = 0.90
, ) Lσ =
ss = F −1(CSL;01
ROP = L ⋅ R + ss =
∫ ( x − RO P ) f ( x ) dx
∞
ESC =
x = RO P
If demand is normal:
ss ss
ESC = − ss 1 − normdist ,0,1,1 + Lσ ⋅ normdist ,0,1,0
Lσ Lσ
ROP 0
Shortage=x-ROP
Upside ROP
0 down
Shortage
LT
Demand 0
During LT 16
utdallas.edu/~metin
Fill Rate
Fill rate: Proportion of customer demand satisfied from stock
Q: Order quantity
ESC
fr = 1 −
Q
17
utdallas.edu/~metin
Evaluating Fill Rate
σ= 500; L = 2 weeks; ss=1000; Q = 10,000;
Fill Rate (fr) = ?
ss ss
ESC = − ss 1 − normdist , + Lσ ⋅ normdist ,0,1,0
Lσ Lσ
,0,11
19
utdallas.edu/~metin
Evaluating Safety Inventory For Given Fill Rate
F ill R a te S a fe ty In v e n to r y
9 7 .5 % 67
9 8 .0 % 183
9 8 .5 % 321
9 9 .0 % 499
9 9 .5 % 767
20
utdallas.edu/~metin
Factors Affecting Fill Rate
Safety inventory: If Safety inventory is up,
– Fill Rate is up
– Cycle Service Level is up.
Lot size: If Lot size is up,
– Cycle Service Level does not change. Reorder point,
demand during lead time specify Cycle Service
Level.
– Expected shortage per cycle does not change. Safety
stock and the variability of the demand during the
lead time specify the Expected Shortage per Cycle.
Fill rate is up.
21
utdallas.edu/~metin
To Cut Down the Safety Inventory
Reduce the Supplier Lead Time
– Faster transportation
» Air shipped semiconductors from Taiwan
– Better coordination, information exchange, advance retailer
demand information to prepare the supplier
» Textiles; Obermeyer case
– Space out orders equally as much as possible
Reduce uncertainty of the demand
– Contracts
– Better forecasting to reduce demand variability
22
utdallas.edu/~metin
Lead Time Variability
E (∑ Di ) = LR Var (∑ Di ) = L ⋅ σ 2 + R 2 ⋅ s 2 =: σ L2
L L
i =1 i =1
ss = F −1
( CSL ; 0 ,1 ) ⋅ σ L = F −1
( CSL ; 0 ,1 ) ⋅ Lσ 2
+ R 2s2
ss ss
ESC = − ss 1 − normdist
;0,1,1 + σ L nomdist ;0,1,0
σ L σ L 23
utdallas.edu/~metin
Impact of Lead Time Variability, s
R = 2,500/day; σ= 500
L = 7 days; Q = 10,000; CSL = 0.90
s ss Jump in ss
0 1695 -
1 3625 1930
2 6628 3003
3 9760 3132
4 12927 3167
5 16109 3182
6 19298 3189 24
utdallas.edu/~metin
Skip this slide and up to (including) p.28
Periodic Review
Order at fixed time intervals (T apart) to raise total inventory
(on hand + on order) to Order up to Level (OUL)
OUL
LT LT 25
utdallas.edu/~metin
Periodic Review Policy: Safety Inventory
T: Reorder interval
σR: Standard deviation of demand per unit time
σL+T: Standard deviation of demand during L+T periods
OUL: Order up to level
R T +L
= (T + L) R
σ T +L
=σ L +T
ss = F −1 (CSL;0,1) ⋅ σ T + L
OUL = R T +L
+ ss
26
utdallas.edu/~metin
Example: Periodic Review Policy
R = 2,500/week; σR = 500
L = 2 weeks; T = 4 weeks; CSL = 0.90
What is the required safety inventory?
ss = F −1 (CSL;0,1) ⋅ σ T + L = 1570
Factors driving safety inventory
– Demand uncertainty
– Replenishment lead time
– Reorder interval
27
utdallas.edu/~metin
Periodic vs Continuous Review
Periodic review ss covers the uncertainty over
[0,T+L], T periods more than ss in continuous case.
Periodic review ss is larger.
Continuous review is harder to implement, use it for
high-sales-value per time products
28
utdallas.edu/~metin
Methods of Accurate Response to Variability
Physical Centralization
Information centralization
– Virtual aggregation, Barnes&Nobles stores
29
utdallas.edu/~metin
Inventory Pooling
Which of two systems provides a higher level of service for a given
safety stock?
Consider demands:
( R 1 , σ 1) ( R 2 ,σ 2 )
(R ,σ R)
C C
( R 3 ,σ 3) ( R 4 ,σ 4 )
∑ R ; (σ ∑σ + 2 ∑ cov( i , j )
k k
= ) =
C C 2 2
R i =1
i R
i =1
i
i≠ j
30
utdallas.edu/~metin
Sum of Identical Random Variables
σ ≤ ∑σ i
k
C
R When they are independent
i =1
σ = ∑σ i
k
C
R When they are perfectly positively
i =1 correlated
σ = 0 ≤ ∑σ i
k
C
R When they are perfectly negatively
i =1 correlated
31
utdallas.edu/~metin
Factors Affecting Value of Aggregation
Demand Correlation, aggregation is helpful almost
always except when products are positively correlated
Coefficient of Variation of demand: Do not bother to
aggregate if the variance is relatively small to begin
with.
32
utdallas.edu/~metin
Impact of Correlation on Aggregated
Safety Inventory (4 outlets)
Benefit=SS after aggregation / SS before aggregation
0.6
0.5
0.4
0.3 Benefit
0.2
0.1
0
0 0.2 0.4 0.6 0.8 1
33
utdallas.edu/~metin
EX 11.8: W.W. Grainger a supplier of
Maintenance and Repair products
About 1600 stores in the US
Produces large electric motors and
industrial cleaners
Each motor costs $500; Demand is
Normal(20,40x40)
Each cleaning can costs $30; Demand is
Normal(1000,100x100)
Which demand has a larger coefficient of
variation?
How much savings if motors inventoried
centrally? How much savings if cleaners
inventoried centrally?
34
utdallas.edu/~metin
EX. 11.8: Specialization: Impact of cv on
Benefit From 1600-Store Aggregation , h=0.25
Motors Cleaner
Mean demand/wk 20 1,000
SD of demand 40 100
Disaggregate cv 2 0.1
Value/Unit $500 $30
Disaggregate ss value $105,600,000 $15,792,000
Aggregate cv 0.05 0.0025
Aggregate ss value $2,632,000 $394,770
Inventory cost savings 102,968,000 15,397,230
Holding Cost Saving $25,742,000 $3,849,308
Saving / Unit $7.74 $0.046
35
utdallas.edu/~metin
Slow vs Fast Moving Items
Low demand = Slow moving items, vice versa.
Slow moving items have high coefficient of variation, vice
versa.
Stock slow moving items at a central store
- “Case Interview” books are not in our sku list. You must check
with our central stores.
- Store keeper at Barnes and Nobles at Collin Creek, March 2002.
36
utdallas.edu/~metin
Product Substitution
Manufacturer driven
Customer driven
One-way substitution
– Army boots. Aggregate?
Two-way substitution:
– Grainger motors; water pumps model DN vs IT.
– Similar products, can customer detect specifications.
If products are very similar, why not to eliminate?
37
utdallas.edu/~metin
Component commonality. Ex. 11.9
Dell producing 27 products with 3 components (processor,
memory, hard drive)
No product commonality: A component is used in only 1
product. 27 component versions are required for each
component. A total of 3*27 = 81 distinct components is
required.
Max component commonality. Only three distinct versions for
each component. Each combination of components is a distinct
product. A component is used in 9 products.
Component commonality provides inventory aggregation.
38
utdallas.edu/~metin
Example 11.9: Value of Component Commonality
in Safety Inventory Reduction
450000
400000
350000
300000
250000
SS
200000
150000
100000
50000
0
1 2 3 4 5 6 7 8 9
40
utdallas.edu/~metin
Disadvantages of Standardization
41
utdallas.edu/~metin
Mass Customization
Mass customization:
– A strategy of producing standardized goods or services,
but incorporating some degree of customization
– Modular design
– Delayed differentiation
42
utdallas.edu/~metin
Mass Customization I: Customize
Services Around Standardized Products
Warranty for contact lenses: Source: B. Joseph Pine
It allows:
– easier diagnosis and remedy of failures
– easier repair and replacement
– simplification of manufacturing and assembly
48
utdallas.edu/~metin
Types of Modularity for Mass
Customization
Cut-to-Fit Modularity,
Gutters that do not require
seams
49
utdallas.edu/~metin
Inventory–Transportation Costs:
Eastern Electric Corporation: p.427
Major appliance manufacturer, buys motors from Westview motors in Dallas
52
utdallas.edu/~metin
Inventory Aggregation at HighMed
Highval ($200, .1 lbs/unit) demand in each of 24 territories
– µH = 2, σH = 5
Lowval ($30/unit, 0.04 lbs/unit) demand in each territory
– µL = 20, σL = 5
UPS rate: $0.66 + 0.26x {for replenishments}
FedEx rate: $5.53 + 0.53x {for customer shipping}
Customers order 1 H + 10 L
53
utdallas.edu/~metin
Inventory Aggregation at HighMed
Current Option A Option B
Scenario
# Locations 24 24 1
Reorder Interval 4 weeks 1 week 1 week
Inventory Cost $54,366 $29,795 $8,474
Shipment Size 8 H + 80 L 2 H + 20 L 1 H + 10 L
Transport Cost $530 $1,148 $14,464
Total Cost $54,896 $30,943 $22,938