Data Analytics in Business

Operations Management

Bob Myers
Lecturer
Scheller College of Business

Inventory Basics
Learning Objectives
At the end of this lesson, you should be able to:
• Discuss the different types of inventory
• Investigate pressures to keep inventory
• Investigate pressures to not keep inventory
• Identify key inventory management decisions
What is Inventory?
• Inventory is the raw material, component parts, work in process, or finished
goods that are held at a location in the supply chain
The Key Activity in Inventory Management
Gap Store
With Clothes Piling Up, Gap Leans on Heavy Discounts to Clear Stores
Executives said operational issues delayed the timing of new items, not because
customers disliked the company’s fashions - by Maria Armental – WSJ May 24, 2018 7:15 p.m. ET
Gap Inc. executives said they had to resort to heavy discounting to move
unsold clothes that had piled up at stores, moves that weighed on profit in the
first quarter and could carry over into the current period.
“If you have too much inventory or the wrong inventory, holding on to it does not
make it better,” Chief Executive Art Peck said on a conference call Thursday. “And
so we were very decisive on that and took those actions. It wasn’t without pain, but
we believe it was absolutely the right thing to do to continue to clean up the
business and position it for better performance.”

Executives blamed operational issues that delayed the timing of new items and
disrupting the assortment of products, but said the weak demand wasn’t the result
of customers disliking the company’s styles or fashions.
How Much Inventory Should You Keep?
Why Keep More Inventory?
• Protects against spikes in demand (uncertain demand)
• Protects against supply disruptions
• Can get a quantity discount on ordering
Why Hold Less Inventory?
• Inventory can become obsolete
• If it is a perishable, it can spoil
• Shrinkage
• Holding Costs
• Insurance, security, warehouse costs, etc..
• Opportunity Costs
The Two I.M. Decisions:
1. HOW MUCH should we order?

2. WHEN should we order more?

Summary
1. Different kinds of inventory
2. Key Ops objective is to
match supply with demand
3. There are pressure to keep
and not keep inventory
4. An inventory management
policy comes down to how
much to order and when to
order.
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

EOQ
Learning Objectives
At the end of this lesson, you should
be able to:
• Explain Economic Order Quantity
The Two I.M. Decisions:
1. HOW MUCH should we order?

2. When should we order more?

Economic Order Quantity
*Tries to balance the scale

Total Cost = Ordering Cost + Inventory Cost

• Ordering Cost = (number of orders per year) X (cost per order)
• Inventory Cost = (average inventory) X (holding cost per year)
Assumptions:

Supplier Retailer Demand

• Demand is known and constant: D units/yr

• We have a known ordering cost, S, and immediate replenishment
• No limit on order quantity
• Annual holding cost of average inventory is H per unit
• Assume Ordering and Inventory costs only relevant costs
Say We Order in Batches of Q

Inventory position

The average
inventory for each
period is…
Time Q
Period over which demand for Q has
occurred

Total Time
Title
Economic Order Quantity = HOW MUCH
• Set Ordering costs equal to Holding cost:
D Q
x S = x H
Q 2

• Solve for Q. We will call this Q* (because it is the Q where Ordering cost
equals Holding cost)

2SD
Q* =
H
How Many Orders Per Year?
• Expected number of orders:
D
N =
Q*

• Expected time between orders:

Number of working days per year

T =
N
Summary
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

EOQ with Quantity Discount

Learning Objectives
At the end of this lesson, you should be able to:
• Examine quantity discounts in the
Economic Order Quantity model
How Can We Account for a Quantity
Discount in the EOQ Model?
How Can we Account for a Quantity Discount?
1. Expand equation for Total Cost to capture purchase price

𝐷 𝑄
• 𝐸𝑥𝑝𝑎𝑛𝑑𝑒𝑑 𝑇𝑜𝑡𝑎𝑙 𝐶𝑜𝑠𝑡 (𝐸𝑇𝐶) = ∗𝑆+ ∗𝐻+𝑷∗𝑫
𝑄 2

D = annual Demand
Q = Quantity Ordered
S = Setup/Order Cost
H = Holding Cost per unit per year
P = Prices per unit
How Can we Account for a Quantity Discount?
2. Calculate an EOQ for each price point
2∗𝐷∗𝑆 I = holding cost as a
𝐸𝑂𝑄 =
𝐼∗𝑃 percent of unit price

3. Adjust EOQ for each price point up or down if needed

to hit that discounts quantity range
How Can we Account for a Quantity Discount?
4. Determine an Expanded Total Cost for each “adjusted” EOQ

5. Pick the lowest Total Cost

Graphic Example

Discount Quantity Price

1 <1,000 $5.00

2 1,000+ $4.80

3 2,000+ $4.75
Summary
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

Re-Order Point
Learning Objectives
At the end of this lesson, you should
be able to:
• Explain Re-order point
The Two I.M. Decisions:
1. How much should we order?

2. WHEN should we order more?

WHEN Should We Order More?
WHEN Should We Order More?
Note Some Similar Assumptions as EOQ
• Demand is known and constant

• Lead time is known and constant

ROP = d x L
Summary
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

ROP When Demand Varies

Learning Objectives
At the end of this lesson, you should
be able to:
• Explain re-order point when demand
can vary
What if We Relax the Constraint on Demand?
• Assume demand is NOT constant
• Assume that demand can be modeled with a probability distribution
• Will add a buffer of extra inventory and call it “safety stock” (ss)
• Size of safety stock will depend on:
• Lead time
• Demand uncertainty
• How strong the desire to NOT stock out
If Actual Demand Less than Expected Demand
If Actual Demand greater than Expected Demand
1

Uncertain Demand – Service Level

Safety Stock: Reduce the Probability of
a Stockout
Service Level
• Service level = probability of NOT stocking out (probability of satisfying
all demand)
• The service level will determine the safety stock
Safety Stock
Safety Stock = (safety factor) x (std. dev. in LT demand)
SS=(z) x (sLT)

Read z from Standard Normal table for a given service level; Service level is G(z)
Standard Deviation in LT Demand
Variance over multiple periods = the sum of the variances of each period
(assuming independence)

Standard deviation over multiple periods is the square root of the

sum of the variances, not the sum of the standard deviations!!!
Putting it Together
ROP = [(average daily demand) * LT] + SS

𝑹𝑶𝑷 = 𝑬𝒙𝒑𝒆𝒄𝒕𝒆𝒅 𝑫𝒆𝒎𝒂𝒏𝒅 𝒅𝒖𝒓𝒊𝒏𝒈 𝒍𝒆𝒂𝒅 𝒕𝒊𝒎𝒆 + 𝒁𝝈𝑫 𝑳𝑻

Z = Number of standard deviations (get from a Z table)

D = standard deviation of demand
LT = Lead Time
Summary
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

ROP When Demand Varies

Example
Learning Objectives
At the end of this lesson, you should be able to:
• Recommend a Re-order point when demand
varies
The Situation:
You work at Best Buy in an Inventory Management role. Your boss wants no
more than a 10% stock out probability and has asked you to recommend a
reorder point for Apple iPads. You review sales data and determine that the
average daily demand for iPads is 15 with a standard deviation of 5 units. The
lead time from Apple for more iPads is 2 days. What reorder point do you
recommend and what portion of that is safety stock?
Solution:
𝑹𝑶𝑷 = 𝑬𝒙𝒑𝒆𝒄𝒕𝒆𝒅 𝑫𝒆𝒎𝒂𝒏𝒅 𝒅𝒖𝒓𝒊𝒏𝒈 𝒍𝒆𝒂𝒅 𝒕𝒊𝒎𝒆 + 𝒁𝝈𝑫 𝑳𝑻

Where: 𝐸𝑥𝑝𝑒𝑐𝑡𝑒𝑑 𝐷𝑒𝑚𝑎𝑛𝑑 𝑑𝑢𝑟𝑖𝑛𝑔 𝑙𝑒𝑎𝑑 𝑡𝑖𝑚𝑒 = 𝐴𝑣𝑒 𝐷𝑒𝑚𝑎𝑛𝑑 ∗ 𝐿𝑇

• Ave Demand = 15 units/day
• Lead Time = 2 days
• D = 5 units

• Z=?
Finding Z:
Normal Distribution

Almost 90%.
Use this Z
value (1.28)
Solution:
𝑹𝑶𝑷 = 𝑬𝒙𝒑𝒆𝒄𝒕𝒆𝒅 𝑫𝒆𝒎𝒂𝒏𝒅 𝒅𝒖𝒓𝒊𝒏𝒈 𝒍𝒆𝒂𝒅 𝒕𝒊𝒎𝒆 + 𝒁𝝈𝑫 𝑳𝑻

Where: 𝐸𝑥𝑝𝑒𝑐𝑡𝑒𝑑 𝐷𝑒𝑚𝑎𝑛𝑑 𝑑𝑢𝑟𝑖𝑛𝑔 𝑙𝑒𝑎𝑑 𝑡𝑖𝑚𝑒 = 𝐴𝑣𝑒 𝐷𝑒𝑚𝑎𝑛𝑑 ∗ 𝐿𝑇

• Ave Demand = 15 units/day
• Lead Time = 2 days
• D = 5 units

• Z = 1.28

ROP = 15*2 + 1.28*5*SQRT(2) = 30 + 9.02 = 39 iPads left, SS~9

Summary
Data Analytics in Business
Operations Management

Bob Myers
Lecturer
Scheller College of Business

Inventory Policy
Learning Objectives
At the end of this lesson, you should
be able to:
• List the two components of an
inventory policy
• Recommend an Inventory Policy when
demand varies
The Two I.M. Decisions:
1. HOW MUCH should we order?

2. WHEN should we order more?

The Situation:
You work at GTRI in their IT group. One of your jobs is building minicomputers
for use by researchers. Keeping costs down is important. Also important is
having the inputs to make minicomputers quickly when requested. Of particular
interest are memory chips. Records show 8,000 units a year on average are
used with a standard deviation of 400. Each unit costs $10 and holding cost is
5%. Each order for more costs $50 and takes a week to arrive. The current
Service Level Agreement (SLA) with R&D is 96%. What inventory policy do you
recommend for this item
How Much?
No quantity discount mentioned in the problem, so use standard EOQ:

When chips are needed based on our ROP (which we will calculate next), we should
order 1,265 chips
When?
Demand is described with “average” and “standard deviation”, this indicates demand varies
ROP = Daily Demand*lead time + Z-score(service level) * daily standard deviation of demand * sqrt(lead time)
Note: ROP is the re-order point. We are looking at the re-order point when demand varies. Please utilize the
ROP equation(s) defined within the course lectures.

ROP = (8000/365)*7 + 1.751* (400/sqrt(365))* sqrt(7)

ROP = 21.9178 * 7 + 1.751 * 20.937 * sqrt(7)

ROP = 250.42 ~ 251 chips

When there are 251 chips left, place an order for 1,265 more
Summary
Operations Management

Bob Myers
Lecturer
Scheller College of Business

Inventory Management
Recap
Learning Objectives
At the end of this lesson, you should
be able to:

• Discuss and recap lessons from

this week
• Assess tie back to analytics
Recap
• There are different kinds of inventory.
• Inventory Management is about
matching supply with demand.
• Even if demand varies, we can make
some optimization decisions.
• We looked at EOQ and ROP to
define an inventory policy.