OPERATIONS ANALYTICS

By Dr. Rajesh Chouksey

Sunday, July 7, 2024 1

Inventory Management
Inventory Management at Amazon.com

► Amazon.com started as a “virtual” retailer

► No inventory
► No warehouses
► No overhead
– just computers taking orders to be filled by others
► Growth has forced Amazon.com to become a world leader in
warehousing and inventory management
Inventory Management at Amazon.com

1. Each order is assigned by computer to the closest distribution

center that has the product(s)
2. A “flow meister” at each distribution center assigns work crews
3. Technology helps workers pick the correct items from the
shelves with almost no errors
4. Items are placed in crates on a conveyor, bar code scanners
scan each item 15 times to virtually eliminate errors
Inventory Management at Amazon.com

5. Crates arrive at central point where items are boxed and

labeled with new bar code
6. Gift wrapping is done by hand at 30 packages per hour
7. Completed boxes are packed, taped, weighed and labeled
before leaving warehouse in a truck
8. Order arrives at customer within 1 - 2 days
Inventory Management

The objective of inventory management is to strike a balance

between inventory investment and customer service
Inventory

• Inventory can be visualized as stacks of money sitting on forklifts, on

shelves, and in trucks and planes while in transit.
• Inventory can be difficult to convert back into cash.
• It is a good idea to try to get your inventory down as far as possible.
Inventory

• For many businesses, inventory is the largest asset on the balance sheet at
any given time.
• A “typical” firm has roughly 30% of its current assets and as much as 90%
of its working capital invested in inventory and as much as 50% of total
invested capital
▶ Less inventory lowers costs but increases chances of running out
▶ More inventory raises costs but always keeps customers happy
Inventory

• Inventory
• A stock or store of goods

• Independent demand items

• Items that are ready to be sold or used
Types of Inventory
▶ Raw material
▶ Purchased but not processed
▶ Work-in-process (WIP)
▶ Undergone some change but not completed
▶ A function of cycle time for a product
▶ Maintenance/repair/operating (MRO)
▶ Necessary to keep machinery and processes productive
▶ Tools and supplies
▶ Finished goods
▶ Completed product awaiting shipment
▶ Pipeline
▶ Goods-in-transit to warehouses or customers
Types of Inventory
• Seasonal Inventory:
• Seasonality in demand is absorbed using inventory
• Decoupling Inventory:
• Complexity of production control is reduced by splitting manufacturing
into stages and maintaining inventory between these stages
• Cyclic Inventory:
• Periodic replenishment causes cyclic inventory
• Pipeline Inventory:
• Exists due to lead time
• Safety Stock:
• Used to absorb fluctuations in demand due to uncertainty
Independent versus Dependent Demand

• The source of demand determines its type

• Independent – Customer demand that is not directly influenced by
the actions of the firm (e.g. customer orders)

• Dependent – Demand that is driven by the plans and activities of

the firm (e.g. components, warehouse demand)
Demand Type

Independent demand – the demands for

various items are unrelated to each other
• For example, a workstation may produce many parts that
are unrelated but meet some external demand
requirement

Dependent demand – the need for any one

item is a direct result of the need for some
other item
• Usually a higher-level item of which it is part
Demand Management and MPC Environment

• DM must conform to the strategy of the firm, capabilities of

manufacturing, and needs of customers
• These define the MPC environment

• MPC environment is defined by customer order decoupling point

• The point where demand changes from independent to dependent
• Alternatively, order penetration point
Make-to-Stock

• Customer demand is filled from finished goods inventory (cosmetics,

grocery items)
• Key focus of demand management is maintenance of finished goods
inventories
• Physical distribution is a key concern
Assemble-to-Order

• Customer requirements are met by a combination of standard options

(personal computers, fast food)
• Primary task of demand management is to define the customer’s
order in terms of components and options (configuration
management)
Make-to-Order

• Items built to customer specifications, starting with raw materials

(airplanes)
• Primary task of demand management is gathering information about
customer needs and coordinating with manufacturing
Engineer-to-Order

• Firm works with the customer to design the product, then produces
the product, starting with raw materials (ships, bridges)
• Primary task of demand management is gathering information about
customer needs and coordinating with engineering and
manufacturing
MPC Environments
Inventory Location

Suppliers Raw Work-in- Finished

materials process goods

Make- Independent Dependent

to-Stock
MPC Environment

Assemble- Independent Dependent

to-Order
Decoupling
Points
Make- Independent Dependent

to-Order

Engineer- Independent Dependent

to-Order
Independent Demand

• Finished goods and spare parts typically belong to independent demand items in
manufacturing organizations
• Two attributes characterize and distinguish independent demand items:
• Timing of demand: Independent demand items have a continuous demand
• Uncertainty of demand: There is considerable element of uncertainty in the demand
in the case of independent demand items
• Inventory planning of independent demand items must address the following two key
questions:
• How much?
• When?
Managing Inventory
Inventory Counting Systems

• Periodic System
• Physical count of items in inventory made at periodic intervals
• Perpetual Inventory System
• System that keeps track of removals from inventory continuously,
thus monitoring current levels of each item
• An order is placed when inventory drops to a predetermined minimum
level
• Two-bin system
• Two containers of inventory; reorder
when the first is empty
Inventory Counting Technologies

• Universal product code (UPC)

• Bar code printed on a label that has information about the item to which it is
attached

• Radio frequency identification (RFID) tags

• A technology that uses radio waves to identify objects, such as goods, in
supply chains
 • ABC Classification (on the basis of consumption value)
Selective
• XYZ Classification (on the basis of unit cost of the item)
Control of • High Unit cost (X Class item)
Inventories • Medium Unit cost (Y Class item)
Alternative • Low unit cost (Z Class item)
Classification • FSN Classification (on the basis of movement of inventory)

Schemes • Fast Moving

• Slow Moving
• Non-moving
• VED Classification (on the basis of criticality of items)
• Vital
• Essential
• Desirable
• On the basis of sources of supply
• Imported
• Indigenous (National Suppliers)
• Indigenous (Local Suppliers)
ABC Classification

• A-B-C approach
• Classifying inventory according to some measure of importance, and
allocating control efforts accordingly
• A items (very important)
• 10 to 20 percent of the number of items in inventory and about 60 to 70
percent of the annual dollar value
• B items (moderately important)
• C items (least important)
• 50 to 60 percent of the number
of items in inventory but only
about 10 to 15 percent of the
annual dollar value
ABC Classification System
Classifying inventory according to some measure of importance, and
allocating control efforts accordingly

• A items (very important)

• 10 to 20 percent of the number of items in inventory and about 60
to 70 percent of the annual value

• B items (moderately important)

• C items (least important)

• 50 to 60 percent of the number of items in inventory but only about
10 to 15 percent of the annual value
ABC ANALYSIS

Percentage of annual dollar usage

80 –
70 –
60 –
50 –
A Items
40 –
30 – B Items
C Items
20 –
10 –
0 – | | | | | | | | | |

10 20 30 40 50 60 70 80 90 100
Percentage of inventory items
ABC Classification
A graphical illustration
 Average Monthly Price per Unit
Problem Item Demand Item
• DAT, Inc., produces digital
audiotapes to be used in 1 700 6
the consumer audio
division. DAT lacks
2 200 4
sufficient personnel in its 3 2,000 12
inventory supply section to
closely control each item 4 1,100 20
stocked, so it has asked 5 4,000 21
you to determine an ABC
classification. Here is a 6 100 10
sample from the inventory
records: Develop an ABC 7 3,000 2
classification for these 10 8 2,500 1
items.
9 500 10
10 1,000 2
 Item Annual Demand Unit Price
Problem
H4-010 20,000 2.5
• Classify the items as A,
B, or C. H5-201 60,200 4
P6-400 9,800 28.5
P6-401 14,500 12
P7-100 6,250 9
P9-103 7,500 22
TS-300 21,000 45
TS-400 45,000 40
TS-041 800 20
V1-001 33,100 4
Boreki Enterprises has the following 10 items in inventory. Theodore
Boreki asks you, a recent OM graduate, to divide these items into ABC
classifications.

a) Develop an ABC classification system for the 10 items.

b) How can Boreki use this information?
c) Boreki reviews the classification and then places item A2 into the A
category. Why might he do so?
 ITEM ANNUAL DEMAND COST/UNIT
DATA A2 3000 50
B8 4000 12
C7 1500 45
D1 6000 10
E9 1000 20
F3 500 500
G2 300 1500
H2 600 20
I5 1750 10
J8 2500 5
• L. Houts Plastics is a large manufacturer of injection-molded plastics
in North Carolina. An investigation of the company’s manufacturing
facility in Charlotte yields the information presented in the table
below. How would the plant classify these items according to an ABC
classification system?
 ITEM CODE # AVERAGE INVENTORY V7ALUE
(UNITS) ($/UNIT)

L. Houts A 400 3.75

Plastics’ B 300 4.00
Charlotte C 120 2.50
Inventory D 75 1.50
Levels E 60 1.75
F 30 2.00
G 20 1.15
H 12 2.05
I 8 1.80
J 7 2.00
K 6 3.00
Inventory MODEL

IDEPENDENT DEMAND - EOQ Model

Inventory Models for Independent Demand

1. Basic economic order quantity (EOQ) model

2. Production order quantity model

3. Quantity discount model

Basic EOQ Model
Important assumptions
1. Demand is known, constant, and independent
2. Lead time is known and constant
3. Receipt of inventory is instantaneous and complete
4. Quantity discounts are not possible
5. Only variable costs are setup (or ordering) and holding
6. Stockouts can be completely avoided
How Much to Order: EOQ Models

• Economic order quantity models identify the optimal order quantity

by minimizing the sum of annual costs that vary with order size and
frequency

1. The basic economic order quantity model

2. The economic production quantity model
3. The quantity discount model
Robust Model
▶ The EOQ model is robust

▶ It works even if all parameters and assumptions are

not met

▶ The total cost curve is relatively flat in the area of the

EOQ
Total Annual Cost

Annual setup cost = (Number of orders placed per year) x (Setup or order cost per order)

Annual demand Setup or order

=
Number of units in each order cost per order
Inventory Usage Over Time
Total order received
Average
Order quantity Usage rate inventory on
= Q (maximum hand
Inventory level

inventory level) Q
2

Minimum
inventory 0
Time
Total Annual Cost

Annual holding cost = (Average inventory level) x (Holding cost per unit per year)

Order quantity
= (Holding cost per unit per year)
2
Total Annual Cost

Annual setup cost = (Number of orders placed per year) x (Setup or order cost per order)

Q* = Optimal number of units per order (EOQ)

 Minimizing Cost : Objective is to minimize total costs
Sum of the two costs
Cost of Inventory

Total cost of carrying

Minimum Cost

Total cost of ordering

Economic Level of Inventory

Order Qty.
Sunday, July 7, 2024 44
Goal: Total Cost Minimization
The Total-Cost Curve is U-Shaped

Annual Cost
Q D
TC  H  S
2 Q

Holding Costs

Ordering Costs

Order Quantity (Q)

QO (optimal order quantity)
Minimizing Costs
Q = Number of pieces per order
Q* = Optimal number of pieces per order (EOQ)
D = Annual demand in units for the inventory item
S = Setup or ordering cost for each order
H = Holding or carrying cost per unit per year

Optimal order quantity is found when annual

setup cost equals annual holding cost

Solving for Q*
Basic EOQ Model

• The basic EOQ model is used to find a fixed order quantity that will minimize total
annual inventory costs
• Assumptions:
1. Only one product is involved
2. Annual demand requirements are known
3. Demand is even throughout the year
4. Lead time does not vary
5. Each order is received in a single delivery
6. There are no quantity discounts
The Inventory Cycle

Cyclic Stock
Quantity

Pipeline inventory

Safety stock
L

Time

Cyclic inventory, pipeline inventory and safety stocks are critically linked to “how much” and “when”
decisions in inventory planning
The Inventory Cycle

Profile of Inventory Level Over Time

Q Usage
Quantity rate
on hand

Reorder
point

Time
Receive Place Receive Place Receive
order order order order order

Lead time
Deriving EOQ

• Using calculus, we take the derivative of the total cost function and set the
derivative (slope) equal to zero and solve for Q.
• The total cost curve reaches its minimum where the carrying and ordering costs
are equal.

𝑄=∗
√ √
2𝐷𝑆 2(annual demand)(order cost)
=
𝐻 annual per unit holding cost
An EOQ Example

Expected number of Demand D

orders =N= = Q*
Order quantity
Expected time Number of working days per year
between orders = T =
Expected number of orders

Total annual cost = Setup cost + Holding cost

ROP = Demand per day * Lead time for a new order in days
ROP = d * L
The demand per day, d, is found by dividing the annual demand, D, by the number of
working days in a year:
d = D / Number of working days in a year
Illustration
A toy manufacturer uses approximately 32,000 silicon chips annually.
The chips are used at a steady rate during the 240 days a year that the
plant operates. Annual holding cost is $3 per chip, and ordering cost is
$120. Determine
a. The optimal order quantity.
b. The number of workdays in an order cycle.
Given Data
D = 32,000 chips per year
S = $120
H = $3 per unit per year
Sunday, July 7, 2024 52
Illustration
Given Data
D = 32,000 chips per year, S = $120, H = $3 per unit per year

√ √
a.
∗ 2 𝐷𝑆 2(annual demand)(order cost)
𝑄= =
𝐻 annual per unit holding cost
∗
𝑄=
3 √
2(32000)(120)
1600 chips

Sunday, July 7, 2024 53

Illustration
Given Data
D = 32,000 chips per year, S = $120, H = $3 per unit per year
b.
Q*/ D = 1600 chips / 32,000 chips/yrs
= 1/20 year
= 1/20*240 days
= 12 days

12 days
Sunday, July 7, 2024 54
Illustration
William Beville’s computer training school, in Richmond, stock
workbooks with the following characteristics:

Demand D = 19,500 units / year

Ordering cost S = $ 25 /order
Holding cost H = $ 4 /unit/year

a) Calculate the EOQ for the workbooks.

b) What are the annual holding costs for the workbooks?
c) What are the annual ordering costs?
Sunday, July 7, 2024 55
Illustration
If D-5 8,000 per month, S-5 $45 per order, and H-5 $2 per unit per
month,

a) What is the economic order quantity?

b) How does your answer change if the holding cost doubles?
c) What if the holding cost drops in half?

Sunday, July 7, 2024 56

Illustration
The Warren W. Fisher Computer Corporation purchases 8,000
transistors each year as components in minicomputers. The unit cost of
each transistor is $10, and the cost of carrying one transistor in
inventory for a year is $3. Ordering cost is $30 per order.
What are
(a) the optimal order quantity,
(b) the expected number of orders placed each year, and
(c) the expected time between orders?
Assume that Fisher operates on a 200-day working year.

Sunday, July 7, 2024 57

Illustration
Given Data
D = 32,000 chips per year, S = $120, H = $3 per unit per year

√ √
a.
∗ 2 𝐷𝑆 2(annual demand)(order cost)
𝑄= =
𝐻 annual per unit holding cost
∗
𝑄=
3 √
2(32000)(120)
1600 chips

Sunday, July 7, 2024 58

An EOQ Example
Determine optimal number of needles to order
D = 1,000 units
S = Rs 10 per order
H = Rs .50 per unit per year
An EOQ Example
Determine optimal number of needles to order
D = 1,000 units
S = Rs 10 per order
H = Rs .50 per unit per year
An EOQ Example
Determine expected number of orders
D = 1,000 units Q* = 200 units
S = Rs 10 per order
H = Rs .50 per unit per year

Expected Demand D
number of = N = =
orders Order quantity Q*
1,000
N= = 5 orders per year
200
An EOQ Example
Determine optimal time between orders
D = 1,000 units Q* = 200 units
S = Rs 10 per order N = 5 orders/year
H = Rs .50 per unit per year

Expected time Number of working days per year

between =T =
orders Expected number of orders

250
T= = 50 days between orders
5
An EOQ Example
Determine the total annual cost
D = 1,000 units Q* = 200 units
S = Rs 10 per order N = 5 orders/year
H = Rs .50 per unit per year T = 50 days
Total annual cost = Setup cost + Holding cost
Numerical
• William Beville’s computer training school, in Richmond, stocks
workbooks with the following characteristics:
• Demand D = 19,500 units / year
• Ordering cost = S = Rs 25 / order
• Holding Cost = H = Rs 4 per unit per year
a)Calculate the EOQ for the workbooks.
b)What are the annual holding costs for the workbooks?
c)What are the annual ordering costs?
Solution

(a)
2(19,500)(25)
EOQ  Q =  493.71  494 units
4

(b) Annual holdings costs = [Q/2]H

= [494/2](4)
= Rs 988
(c) Annual ordering costs = [D/Q]S
= [19500/494](25)
= Rs 987
Numerical

• If D = 8000 per month, S = Rs 45 per order, and H = Rs 2 per unit per

month,

a)What is the economic order quantity?

b)How does your answer change if the holding cost doubled?
c)What if the holding cost drops in half?
Solution

(a)
2(8,000)(45)
EOQ   600 units
2
(b) If H doubles, from Rs 2 to Rs 4/unit/month,

2 8,000 45
EOQ = = 424.26 units
4

(c) If H drops in half, from Rs 2 to Rs 1/unit/month,

2 8,000  45
EOQ   848.53 units
1
Numerical

• Henry Crouch’s law office has traditionally ordered ink refills 60 units
at a time. The firm estimates that carrying cost is 40% of the Rs 10
unit cost and that annual demand is about 240 units per year. The
assumptions of the basic EOQ model are thought to apply.
a)For what value of ordering cost would its action be optimal?
b)If the true ordering cost turns out to be much greater than your
answer to (a), what is the impact on the firm’s ordering policy?
Solution

(a) This problem reverses the unknown of a standard EOQ problem to solve for S.

2  240  S 480 S
60  ; or 60  , or
.4  10 4
3,600
60  120 S , so solving for S results in S   $30.
120
(a) S = Rs 30

(b)If S were Rs 30, then the EOQ would be 60.

If the true ordering cost turns out to be much
greater than RS 30, then the firm’s order policy is
ordering too little at a time.
Solution
An Apple store has a demand (D) for 8,000 iPhones per year. The firm operates a
250-day working year. On average, delivery of an order takes 3 working days, but
has been known to take as long as 4 days. The store wants to calculate the reorder
point without a safety stock and then with a one-day safety stock.

d = D / Number of working days in a year

= 8,000 / 250
= 32 units

ROP = Reorder point = d * L

= 32 units per day * 3 days
= 96 units
Thank You!

Sunday, July 7, 2024 71