Managing uncertainty in supply chain:

Safety Inventory
 The Role of Safety inventory in Supply Chain

Safety inventory is inventory carried to satisfy demand that exceeds the amount
forecast. Safety inventory is required because demand is uncertain, and a product
shortage may result if actual demand exceeds the forecast demand.

Consider an example, a retail store sells product purchased from manufacturer.

Given the high transportation cost, the store manager at orders in lots of 600
products. Demand for products at the retail store is 100 products in a week.
Manufacturers takes three weeks to deliver the products to the store in response to
an order. If there is no demand uncertainty and exactly 100 products are sold
each week, the store manager can place an order when the store has exactly 300
products remaining. In the absence of demand uncertainty, such a policy ensures
that the new lot arrives just as the last product is being sold at the store
 The Role of Safety inventory in Supply Chain
Due to demand uncertainty and forecasting errors, actual demand over the three weeks
may be higher or lower than the 300 product that were forecast.

• If the actual demand at store is higher than 300, some customers will be unable to
purchase product, resulting in a potential loss of margin for store.

• The store manager thus decides to place an order with manufacturer when the store
still has 400 products. This policy improves product availability for the customer
because the store now runs out of product only if the demand over the three weeks
exceeds 400.

• Given an average weekly demand of 100 products, the store will have an average of
100 products remaining when the replenishment lot arrives. Safety inventory is the
average inventory remaining when the replenishment lot arrives.
 The Role of Safety inventory in Supply Chain

Average Inventory = Cycle

Inventory + Safety Inventory

 There is a trade-off that a supply chain manager must consider when planning safety
inventory. On one hand, raising the level of safety inventory increases product
availability and customer service. On the other hand, raising the level of safety
inventory increases inventory holding costs.
 The Role of Safety inventory in Supply Chain
For any supply chain, three key questions need to be considered when planning
safety inventory:

• What is the appropriate level of product availability?

• How much safety inventory is needed for the desired level of product
availability?

• What actions can be taken to reduce safety inventory without hurting product
availability?
 Factors affecting the level of safety inventory

The appropriate level of safety inventory is determined by the following two

factors:
• The uncertainty of both demand and supply
• The desired level of product availability
As the uncertainty of supply or demand grows, the required level of safety
inventories increases.
Demand for milk at a supermarket is quite predictable. As a result, supermarkets
can operate with low levels of safety inventory relative to demand.
 Measuring the Demand Uncertainty

Demand has a systematic component and a random component

The estimate of the random component is the measure of demand uncertainty
Random component is usually estimated by the standard deviation of demand
Notation:
D = Average demand per period
= standard deviation of demand per period
L = lead time = time between when an order is placed and when it is received
 Uncertainty of demand during lead time is what is important.
Basically we are focusing on the demand variation during the lead time.
 Measuring the Demand Uncertainty
If demand during each of L periods is independent and normally distributed
with a mean of D and a standard deviation of , then the total demand during
the L periods is normally distributed with a mean and a standard deviation of
, where

Another important measure of uncertainty is the coefficient of variation (cv),

which is the ratio of the standard deviation to the mean. Given demand with a
mean of and a standard deviation of , we have
 Measuring the Product Availability (Impact of Service
Level on Safety Stock)
Product availability: a firm’s ability to fill a customer’s order out of available inventory
Stockout: a customer order arrives when product is not available
It is very difficult to measure stockout costs.
A service level of 100 percent means that there will be never a stockout situation and all
demands are served from stock.
There are two popular ways in which service levels are expressed:
• Service level is the probability that all orders will be filled from stock during the
replenishment lead time or during the reorder cycle. This is known as cycle service
level.
• Service level is a percentage of demand filled from stock during a given period of
time for example a year. This is known as fill rate. Assume that a company provides
smartphones to 90 percent of its customers from inventory, with the remaining 10
percent lost to a neighboring competitor because of a lack of available inventory. In
this case, the company achieves a fill rate of 90 percent
 Replenishment Policies

Replenishment policy: decisions regarding when to reorder and how much to reorder.
Replenishment policies may take any of several forms. We restrict attention to two types:
• Continuous review: inventory is continuously monitored and an order of size Q is placed
when the inventory level reaches the reorder point (ROP).
As an example, consider the store manager at company who continuously tracks the
inventory of phones. She orders 600 phones when the inventory drops below ROP =
400. In this case, the size of the order does not change from one order to the next. The
time between orders may fluctuate, given variable demand.
• Periodic review: inventory is checked at regular (periodic) intervals and an order is
placed to raise the inventory to a specified threshold (the “order-up-to” level).
 Determining the appropriate level of safety inventory

To determine the appropriate level of safety inventory, we only consider the
continuous review policy.
The continuous review policy consists of a lot size Q ordered when the inventory
on hand declines to the ROP. Assume that weekly demand is normally distributed,
with mean D and standard deviation Assume the replenishment lead time is L
weeks.
 Expected demand during the lead time is =
 Safety Stock for the continuous replenishment policy is
Determining the appropriate level of safety inventory

Weekly demand follows normal distribution with mean of 2500 and

standard deviation of 500.
D = 2500 and
Reorder Point (ROP) = 6000.
Order quantity = 10000 and lead time (L) = 2 weeks
Expected demand during lead time =
Safety Stock =
Evaluating safety inventory based on a desired service
level (Continuous Review Replenishment Policy)
Continuous Review (Q) System

Mean demand during LT

Safety Stock
Time
Evaluating safety inventory based on a desired service level
(Continuous Review Replenishment Policy)
Our goal is to obtain the appropriate level of safety inventory given the desired
CSL. We assume that a continuous review replenishment policy is followed.
Given a lead time of L, the store manager wants to identify a suitable reorder
point ROP and safety inventory that achieves the desired service level. Assume
that demand is normally distributed and independent from one week to the next.
We assume the following inputs
• Desired cycle service level = CSL
• Mean demand during lead time =
• Standard deviation of demand during lead time =
• We know that . The store manager needs to identify safety inventory ss such that
the following is true:
Evaluating safety inventory based on a desired service level

In continuation of the previous slide,

Safety stock value will be

Or,
*The value of will be provided. [ means inverse of normal distribution]
Or, we can represent the safety stock as , Where Z value we will get from the Z
table based on cycle service level.
 Evaluating safety inventory based on a desired service level

Demand during lead time =

Standard deviation of demand during lead time is =
Cycle Service Level (CSL) = 0.90
Safety Stock =
[The value of NORMSINV(.90) is 1.281]
Or, Safety Stock . [the value of z at the 90 percent service level is 1.281]

* We are not considering the demand uncertainty due to supply in your syllabus. That’s it all about
managing uncertainty in supply chain : safety inventory.
Evaluating safety inventory based on a desired service level

Demand during lead time =

Standard deviation of demand during lead time is =
Cycle Service Level (CSL) = 0.95
Safety Stock . [the value of z at the 95 percent service level is 1.64]
Evaluating Safety inventory at a desired service level
(Periodic Review)

Periodic Review (P) System

• Fixed period review for ordering, but Order quantity may vary.

• Inventory position (IP) is checked after every review period T.

• Order is placed so that the inventory position reaches a predetermined level or “order- up-
to- level” (OUL) = S. So quantity of order is S – IP.
Evaluating Safety inventory at a desired service level
(Periodic Review)
Evaluating Safety inventory at a desired service level
(Periodic Review)
• The store manager places the first order at time (t = 0) such that the lot size ordered and
the inventory position sum to the OUL.
• Once an order is placed, the replenishment lot arrives after the lead time L.
• The next review period is time T, when the store manager places the next order, which
then arrives at time (T+L).
• The store will experience a stockout if demand during the time interval between 0 and (T
+ L) exceeds the OUL
Probability (demand during T+L<=OUL) = CSL
• Safety Stock = [Z is the z-value of the desired cycle service level]
• OUL = Expected demand during (T+L) + Safety Stock =
Comparison of Q and P systems of inventory control
Criterion Continuous Review (Q) Periodic Review (P)
System System
How much to Fixed order quantity: Q S= µ(L+T) + Zα * σ(L+T)
order QT= S - IT
When to order ROP= µ(L) + Zα * σ(L) Every T periods
Safety stock SS= Zα * σ(L) SS= Zα * σ(L+T)
Salient aspects Implemented using two More safety stock
bin system More responsive to
Suited for medium and demand
low value items Ease of ordering in case
of multiple items from
same supplier
Illustrative Example:
A manufacturing organization is using a certain raw material, which is consumed in large
quantities by various products. The raw material is procured from a local supplier. An
extract of the relevant records from the stores indicates the following details about the
component:

Mean of weekly demand: 200

Standard Deviation of weekly demand : 40
Unit cost of the raw material : Rs. 300
Ordering cost : Rs. 460 per order
Carrying cost percentage: 20% per annum
The purchase department has indicated that the lead time for procurement of this raw
material is two weeks.
EOQ Model
Weekly demand = 200
No. Of weeks per year = 52
Annual demand, D = 200* 52 = 10400
Ordering cost, Co = Rs. 460.00 per order
Unit cost of the item = Rs. 300.00
So, inventory carrying cost, Cc = Rs. 60 per unit
per year
Economic Order Quantity = = 399.33 = 400 (approx)
Time between orders = 400/10400 = 2/52 = 2 weeks
Q System (Continuous Review System)

Standard Deviation of weekly demand = 40

Lead time, L = 2 weeks
Expected demand during L = 2*200 = 400
Standard Deviation of demand during L,
σ(L) = 40 = 56.57
For a service level of 95%,
SS = Z * σ(L) = 1.645*56.57 = 93.05
ROP = Expected Demand during lead Time + Z * σ(L) = 400 + 93 = 493

Using EOQ as the fixed order quantity, the Q system can be designed such that, as the
inventory position in the system reaches 493, an order is placed for 400 units. In the
long run this will ensure a service level of 95 percent.
P System (Periodic Review System)

Using the time between orders derived from the EOQ model as the basis for review period.
Review period, T = 2 weeks
Expected demand during (L+T) = 200*(2+2) = 800
Standard Deviation of demand during (L+R),
σ(L+R) = 40 = 80
For a service level of 95%,
SS = σ(L+T) = 1.645*80 = 131.6
Order up to level , S = Expected demand during (L+T) + σ(L+T)
= 800 +132 = 932
The P system can be designed such that the inventory position in the system is reviewed
every two weeks and an order is placed to restore the inventory position back to 932 units.
This will ensure a service level of 95 percent.
Effect of Centralized and Decentralized System on
Inventory – Risk Pooling
• Demand variability is reduced if one aggregates demand across locations.
• More likely that high demand from one customer will be offset by low demand
from another.
• Reduction in variability allows a decrease in safety stock and therefore reduces
average inventory.
• Demand Variation can be measured by Standard deviation and coefficient of
variation.
Example
• Electronic equipment manufacturer and distributor
• 2 warehouses for distribution in Location A and Location B (partitioning the market into
two regions)
• Customers (that is, retailers) receiving items from warehouses (each retailer is assigned a
warehouse)
• Warehouses receive material from Chicago. Lead time for delivery to each of the
warehouses is about 1 week.
• Current rule: 97 % service level
• Each warehouse operate to satisfy 97 % of demand (3 % probability of stock-out)
• Replace the 2 warehouses with a single warehouse (located some suitable place) and try
to implement the same service level 97 %
• Delivery lead times may increase.
• But may decrease total inventory investment considerably.
Historical Data
PRODUCT A
Week 1 2 3 4 5 6 7 8
Location 1 33 45 37 38 55 30 18 58
Location 2 46 35 41 40 26 48 18 55
Total 79 80 78 78 81 78 36 113
PRODUCT B
Week 1 2 3 4 5 6 7 8
Location 1 0 3 3 0 0 1 3 0
Location 2 2 4 3 0 3 1 0 0
Total 2 6 3 0 3 2 3 0
Summary of the historical data
Statistics Product Average Demand Standard Coefficient of
Deviation of Variation
Demand
Location 1 A 39.3 13.2 0.34
Location 1 B 1.125 1.36 1.21
Location 2 A 38.6 12.0 0.31
Location 2 B 1.25 1.58 1.26
Total A 77.9 20.71 0.27
Total B 2.375 1.9 0.81
Example
For each product, the average demand faced by the warehouse in the centralized
distribution system is sum of the average demand faced by the each existing warehouse.

The Variability faced by the central distribution system, measured by standard deviation
or coefficient of variation is smaller than combined variability faced by two existing
warehouse.

This has a major impact on inventory levels in the current and proposed system.
Inventory Levels
Product Average Safety Reorder Q
Demand Stock Point
During Lead
Time
Location 1 A 39.3 24.8 64 132
Location 1 B 1.125 2.57 4 25
Location 2 A 38.6 22.8 62 131
Location 2 B 1.25 3 5 24
Total A 77.9 39.35 118 186
Total B 2.375 3.61 6 33

For both the product an order from the factory cost $60 per order and holding costs are $0.27 per
unit per unit time. Based on EOQ formula we have calculated the values of Q column.
Saving in Inventory
Average inventory for Product A:
• At location 2 warehouse is about 88 units
• At location 1 warehouse is about 91 units
• In the centralized warehouse is about 132 units
• Average inventory reduced by about 36 percent
Average inventory for Product B:
• At location 2 warehouse is about 15 units
• At location 1 warehouse is about 14 units
• In the centralized warehouse is about 20 units
• Average inventory reduced by about 43 percent
Critical Points
The higher the coefficient of variation, the greater the benefit from risk pooling.

• The higher the variability, the higher the safety stocks kept by the warehouses. The
variability of the demand aggregated by the single warehouse is lower.

The benefits from risk pooling depend on the behavior of the demand from one market
relative to demand from another.

• risk pooling benefits are higher in situations where demands observed at warehouses
are negatively correlated

Reallocation of items from one market to another easily accomplished in centralized

systems. Not possible to do in decentralized systems where they serve different markets.
Centralized Vs Decentralized System
• Safety stock: lower with centralization
• Service level: higher service level for the same inventory investment
with centralization
• Overhead costs: higher in decentralized system
• Customer lead time: response times lower in the decentralized system
• Transportation costs: not clear. Consider outbound and inbound costs.
 Example
• Magazine Luiza is a Brazilian retail chain for consumer electronics. The company
currently has 100 stores distributed across Brazil. It also operates an online channel. It is
considering introduction of a new printer and must decide whether to offer it at retail
stores or the online channel. Weekly demand for the printer at each store has been forecast
to be normally distributed with a mean of 100 and a standard deviation of 80. The
company has also forecast that the demand at the online channel would be the sum of
demand across all 100 stores. The supplier will take four weeks to fulfill a replenishment
order, whether placed separately by each store or by the online DC. Magazine Luiza is
targeting a CSL of 95 percent and monitors its inventory continuously. How much safety
inventory will Magazine Luiza carry if the printer is carried at all 100 stores? How much
safety inventory will Magazine Luiza carry if the printer is carried online and demand
across stores is independent?
 Impact of Product Type on Centralization
• Assume a supplier of MRO products, has 1,600 stores distributed throughout the United
States. Consider two products—large electric motors and industrial cleaner. Large electric
motors are high-value items with low demand, whereas the industrial cleaner is a low-
value item with high demand. Each motor costs $500 and each can of cleaner costs $30.
Weekly demand for motors at each store is normally distributed, with a mean of 20 and a
standard deviation of 40. Weekly demand for cleaner at each store is normally distributed,
with a mean of 1,000 and a standard deviation of 100. Demand experienced by each store
is independent, and supply lead time for both motors and cleaner is four weeks. The
annual holding cost of 25 percent. For each of the two products, evaluate the reduction in
safety inventories that will result if they are removed from retail stores and carried only in
a centralized DC. Assume a desired CSL of 0.95.
 Blank Motors Cleaner
Inventory is stocked in each store Blank Blank
Mean weekly demand per store 20 1,000
Standard deviation 40 100
Coefficient of variation 2.0 0.1
Safety inventory per store 132 329
Total safety inventory 211,200 526,400
Value of safety inventory $105,600,000 $15,792,000
Inventory is aggregated at the DC Blan Blank
Mean weekly aggregate demand 32,000 1,600,000
Standard deviation of aggregate demand 1,600 4,000
Coefficient of variation 0.05 0.0025
Aggregate safety inventory 5,264 13,159
Value of safety inventory $2,632,000 $394,770
Total inventory saving on aggregation $102,968,000 $15,397,230
Total holding cost saving on aggregation $25,742,000 $3,849,308
Holding cost saving per unit sold $15.47 $0.046
Total holding
cost/(32000*52)
Savings as a percentage of product cost 3.09% 0.15%
Item Type Centralized Inventories Decentralized Inventories
Fast Moving Predictable Customer willing to pay Low cost
{Low Value} premium?
Slow Moving Unpredictable Low cost Customer willing to pay premium?
{High Value}