Managing Uncertainty in Supply

Chain: Safety Inventory – Chap 12

 Safety Inventory
• Safety inventory is carried to satisfy
demand that exceeds the amount
forecasted for a given period

• It is the average inventory remaining when

the replenishment lot arrives
The Role of Safety Inventory
 Safety Inventory
• Raising the safety inventory increases
product availability, but also increases
inventory holding costs

• The issue is particularly significant in

industries in which product life cycles are
short and demand volatile.
– Inventory on hand in such situation becomes
worthless
 Factors Affecting Level of
Safety Inventory
• The level of safety inventory is determined by
two factors
– The uncertainty of demand and supply
• Higher uncertainty in demand leads to higher
safety inventory
– Milk: Low uncertainty → low safety inventory
– Spices: High uncertainty → high safety
inventory
• Higher uncertainty in supply leads to higher safety
inventory
– If LT decreases by k, the required safety
inventory decreases by a factor √k.
 Factors Affecting Level of
Safety Inventory
– The desired level of product availability
• Ability to fill a customer order out of available
inventory
– Product fill rate →fraction of product demand that
is satisfied from product in inventory. Measured
over specifics amounts of demand
– Order fill rate→ fraction of orders that are filled
from available inventory. Measured over specific
number of orders.
– Cycle service level →fraction of replenishment
cycles that end with all the customer demand being
met. It is the interval between two successive
replenishment deliveries
 Factors Affecting Level of
Safety Inventory
• Difference between product fill rate and order fill rate is not
significant in a single product situation, but significant in
multiple product case.

• As the desired product availability goes up, the required

safety inventory also increases because the supply chain
must now be able to accommodate uncommonly high demand
or uncommonly low supply.
 Safety Inventory
• In recent years, product variety has grown
but product life cycle has shrunk
– Product that is “hot” today is likely to be
become obsolete tomorrow leading to too
much inventory and associated hold cost
• Key to success in supply chain is to
determine ways to decrease the level of
safety inventory with hurting product
availability
 Two Managerial Levers to
Reduce Safety Inventory
• Reduce the uncertainty in demand
– Better market intelligence, sophisticated
forecasting methods, increased supply chain
visibility
• Reduce supplier lead time
– Flexible production methods, faster methods
of transport, supplier part closer to parent
facility
Variance Sum Law II
 Impact of Aggregation on
Safety Inventory

• How does aggregation affect forecast accuracy and

safety inventories
Di: Mean weekly demand in region i, i = 1,…, k regions
si: Standard deviation of weekly demand in region i, i =
1,…, k
rij: Correlation of weekly demand for regions i, j,
1≤i≠j≤k
 Impact of Aggregation on
Safety Inventory
• There are two ways to serve demand
– Have local inventories in each region
– Aggregate all inventories into one centralized
facility
 Impact of Aggregation on
Safety Inventory
Total safety inventory in k
 z LT  s i
decentralized option i 1

If all inventories are aggregated in a central location

k
D =å D; ( )
var D = ås + 2å r s s ;
C k C 2
i=1 i i ij i j
i=1 i> j

s = var D
C
D ( ) C

If all k regions have demand that is independent (ρij =0), and identically
distributed, with mean D and standard deviation σD, then above equation becomes

DC = kD s DC = k s D
 Impact of Aggregation on
Safety Inventory

k
  z  L  s DC
Require safety inventory on
aggregation i 1

If correlation of demand across any pair of areas is ρ

Holding-cost savings on aggregation per unit sold

FS–1(CSL) ´ L ´ H æk ö
= ´ ççås i – s D ÷÷
C

DC è i=1 ø
 Impact of Aggregation on
Safety Inventory

• The safety inventory savings on aggregation increase with the

desired cycle service level CSL
• The safety inventory savings on aggregation increase with the
replenishment lead time L
• The safety inventory savings on aggregation increase with the
holding cost H
• The safety inventory savings on aggregation increase with the
coefficient of variation of demand
• The safety inventory savings on aggregation decrease as the
correlation coefficients increase
 Key Learning
• Aggregation reduces demand uncertainty
– and thus safety inventory—as long as
demand being aggregated is not perfectly
positively correlated
 Inventory at Multiple Locations
(The Square Root Law)
• If demand in different regions is about the same
size and independent, aggregation reduces
safety inventory by the square root of the
number of regions aggregated

• The square root law states that total safety

stock inventories in a future number of facilities
can be approximated by multiplying the total
amount of inventory at existing facilities by the
square root of the number of future facilities
divided by the number of existing facilities
 Inventory at Multiple Locations
(The Square Root Law)

X2 = X1√(n2/n1)

Where n1 = # of existing facilities

n2 = # of future facilities
X1 = Total inventory in existing
facilities
X2 = Total inventory in future facilities
Square-Root Law
 Problem
(Square Root Law)
• A company operated 16 regional
warehouses. Each warehouse carried
$165,000 inventory on average. If all
stocks are to be consolidated into one
location, how much inventory can be
expected?

TOTAL INVENTORY = 165000*16 = 2640000

 Square Root Law
• Solution
X2 = X1√(n2/n1)
X2 = 165000×16√(1/16) = $660,000

• Question: If consolidated in two locations that

equally divide the stock, how much inventory
can be expected in each warehouse?
• X2 = $165000×16×√(2/16) = $933381
• Reduction in inventory: $2640000 - $933381
=$1,706,619
 Square Root Law
• If the number of independent stocking
locations decreases by a factor “n”, the
average safety inventory is expected to
decrease by a factor of “√n”
 Benefits of Aggregating Safety
Inventories
• Information centralization
– Gap and Walmart can use information system
to inform customers of the closest store with
the product in inventory
• Specialization
– If reduction in safety inv. high→ Central
location
– If reduction in safety inv. low→ Multiple
decentralized locations
Safety Inventory and Demand’s
Coefficient of Variation
• For a product with a low coefficient of
variation, disaggregate demand can be
forecast with accuracy
– Benefit of aggregation is minimal
• High coefficient of variation of demand,
disaggregate demand is difficult to
forecast
– Benefit of aggregation is substantial
 Impact of Item movement on
Safety Inventory
• Fast moving items → decentralized locations
• Slow moving items → centralized locations
 Component Commonality and
Inventories
• When a supply chain is producing a large
variety of products, components can easily
become very large. The use of common
components in a variety of products is an
effective supply chain strategy to exploit
aggregation and reduce component
inventories.
 Two Major Disadvantages of Aggregating
Inventories in One Location
• Increase in response time
• Increase in transportation cost to customer

Both disadvantages result because of the average distance between

inventory and the customer increases with aggregation
 Postponement
• Postponement is the ability to delay
product differentiation or customization
until closer to the time the product is sold.