SUPPLY CHAIN

PROFITABILIT Y
BASIC INVENTORY THEORY - EOQ

2𝐾𝐷
Economic Order Quantity, Q =
𝐻

where, 𝐾 = Inventory Ordering Cost; 𝐷 = Annual Demand

H = Unit Inventory Holding Cost

Reorder Point, R = 𝐿𝐷/365

where, L = Supply/Replenishment Lead Time
SAFETY INVENTORY

L: Lead time for replenishment = DL

D: Average demand per unit time
D L

D: Standard deviation of demand  L

= L D
ss = F S (CSL)  L
DL: Mean demand during lead time −1

L: Standard deviation of demand

during lead time ROP = D L + ss
CSL: Cycle service level CSL = F ( ROP, D L , L )
ss: Safety inventory
ROP: Reorder point

Average Inventory = Q/2 + ss

FILL RATE
• Proportion of customer demand satisfied
from stock ESC
fr = 1 −
Q
• ESC is the expected shortage per
cycle (average demand in excess of  ss 
reorder point in each replenishment ESC = − ss{1 − F S  }
cycle)  L 
 ss 
• ss is the safety inventory +  L f S  
 L 
• Q is the order quantity

ESC = -ss{1-NORMDIST(ss/L, 0, 1, 1)} + L NORMDIST(ss/ L, 0, 1, 0)

SAFETY INVENTORY

Fill Rate Safety Inventory

97.5% 67
98.0% 183
98.5% 321
99.0% 499
99.5% 767
SAFETY STOCK – SUPPLY UNCERTAINTY

Safety Inventory, ss = 𝑧 ∗ 𝐿𝜎𝐷 2 + 𝜇𝐷 2 𝑠𝐿 2

where, 𝜇𝐷 = Mean demand; z is constant
𝜎𝐷 = Standard Deviation of Demand;
𝑠𝐿 = Standard Deviation of Lead Time
IMPACT OF SUPPLY UNCERTAINTY

Safety inventory when sL = 0 is 1,695

Safety inventory when sL = 1 is 3,625
Safety inventory when sL = 2 is 6,628
Safety inventory when sL = 3 is 9,760
Safety inventory when sL = 4 is 12,927
Safety inventory when sL = 5 is 16,109
Safety inventory when sL = 6 is 19,298
THE NEWSVENDOR

𝒑−𝒄 𝒑−𝒄 𝑪𝒖
Service Level = = =
𝒑−𝒔 𝒑−𝒄+𝒄−𝒔 𝑪𝒖 +𝑪𝑶
Q.1
Consider a buyer at Blomingdales responsible for purchasing dinnerware with
Christmas patterns. The dinnerware only sells over Christmas season and the
buyer places an order for delivery in early November. Each dinnerware set
costs 𝑐 = $100 and sells for a retail price 𝑝 = $250. Any set unsold by
Christmas are heavily discounted in the post-Christmas sales and sold for a
salvage value of 𝑠 = $80. The buyer has estimated that demand is normally
distributed with a mean of 𝜇 = 350. Historically, forecast errors have had a
standard deviation of 𝜎 = 150. The buyer has decided to conduct additional
market research to get a better forecast. Evaluate the impact of improved
forecast accuracy on profitability and inventories as the buyer reduces 𝜎 from
150 to 0 in increments of 30.
Solution
Profit
53000
Cost of Understocking 150 52000
Cost of Overstocking 20 51000
CSL* 0.882352941 50000
49000
Mean demand, mu 350
48000
47000 Profit
46000
45000
44000
0.01 30 60 90 120 150

Standard
Deviation of Expected Expected
Demand, 𝝈 Order Size Profit Overstock Understock
0.01 350.01 52499.66 0.01 0.00
30 385.60 51493.96 37.33 1.73
60 421.21 50487.93 74.67 3.46
90 456.81 49481.89 112.00 5.19
120 492.42 48475.86 149.34 6.92
150 528.02 47469.82 186.67 8.65
REDUCE DEMAND UNCERTAINTY
• Improved forecasting
– Through better market intelligence and collaboration

• Quick Response
– Reduce lead time and multiple orders

• Postponement
– Postpone product differentiation

• Tailored Sourcing
– Use responsive supplier as backup
FORECASTING WOES
•Behavioral

•Procedural

•Forecasting done in the absence of information

•Long lead time leads to more forecast errors

•Bullwhip Effect
REPLENISHMENT LEAD TIME

Quick Response is rewarding

Q.2

The Saks Fifth Avenue, a high-end department store, purchasing cashmere shawls from
India and Nepal. The selling season for cashmere shawls is about 14 weeks. Historically,
replenishment lead times have been 30 weeks. The buyer of Saks must order all the store
expects to sell well before the start of the selling season. The buyer of Saks must decide on
the quantity of cashmere shawls to order from India and Nepal for the upcoming winter
season. The unit cost of each shawl is $40, and the shawl retails for $150. A discount store
purchases any leftover shawls at the end of the season for $30 each. After the sales season
of 14 weeks, any leftover shawls are sold to the discount store.

Before the start of the sales season, the buyer forecasts weekly demand to be normally
distributed with a mean of 20 and a standard deviation of 15. Evaluate the following:

(1) Supply lead time is 15 weeks. As a result, a single order must be placed at the
beginning of the season to cover the entire season’s demand.

(2) Supply lead time is reduced to six weeks. As a result, two orders are placed for the
season, one to be delivered at the beginning of the season and the other to be placed at
the end of week 1 and delivered at the beginning of week 8.

(3) By adopting a quick response system, there is an improvement in the forecast accuracy
in the form of reduction in the standard deviation from 15 to 3.
 SOLUTION

Price of the product, p 150 Mean Daily Demand 20

Cost of the product, c 40 Standard Deviation 15
Salvage Value, s 30

Cost of Understocking 110 Cost of Overstocking 10

CSL* 0.916666667

Option 1 Mean demand, 𝜇 280 SD of Demand, 𝜎 56.1248608

Sigma Order Size Profit Expected Overstock Expected Understock

56.1248608 357.62 $29,767.44 79.76 2.14

Option 2 Mean demand, 𝜇 140 SD of Demand, 𝜎 39.68626967

SD of Demand, 𝜎 Order Size Profit Expected Overstock Expected Understock

39.68626967 194.89 $14,669.87 56.40 1.51
194.89 Total Profit $29,903.71

Option 3 Mean demand, 𝜇 140 SD of Demand, 𝜎 7.937253933

SD of Demand, 𝜎 Order Size Profit Expected Overstock Expected Understock

7.937253933 150.98 $15,253.97 11.28 0.30
Total Profit $30,036.64
 Reduce Forecast Errors
• Improved forecasting
– Through better market intelligence and collaboration

• Quick Response
– Reduce lead time and multiple orders

• Aggregation of Demand
– Postponement - Postpone product differentiation

• Tailored Sourcing
– Use responsive supplier as backup

• Supply Chain Coordination

– Information Sharing

– Collaborative Forecasting and Planning

– Single Stage of Control

– Supply Contract
Risk Pooling – The Benefits of Aggregation
No Aggregation – Safety Stock

Warehouse Mean SD of
Location Demand* Demand
Chandigarh 𝜇1 = 100 𝜎1 = 23
Delhi 𝜇2 = 345 𝜎2 =85
Ahmedabad 𝜇3 = 267 𝜎3 = 67
Kanpur 𝜇4 = 154 𝜎4 = 54
Guwahati 𝜇5 = 121 𝜎5 = 34
Bhopal 𝜇6 = 212 𝜎6 = 45
Kolkata 𝜇7 = 285 𝜎7 = 64
Mumbai 𝜇8 = 387 𝜎8 = 93
Bhubaneswar 𝜇9 = 201 𝜎9 = 38
Hyderabad 𝜇10 = 254 𝜎10 = 54
Bangalore 𝜇11 = 323 𝜎11 = 88
Chennai 𝜇12 = 276 𝜎12 = 74
* In thousand units
No Aggregation – Safety Stock

Warehouse SD of Safety Stock@90%

Location Demand Service Level
Chandigarh 𝜎1 = 23 29.47
Delhi 𝜎2 =85 108.93
Ahmedabad 𝜎3 = 67 85.86
Kanpur 𝜎4 = 54 69.20
Guwahati 𝜎5 = 34 43.57
Bhopal 𝜎6 = 45 57.67
Kolkata 𝜎7 = 64 82.02
Mumbai 𝜎8 = 93 119.18
Bhubaneswar 𝜎9 = 38 48.70
Hyderabad 𝜎10 = 54 69.20
Bangalore 𝜎11 = 88 112.78
Chennai 𝜎12 = 74 94.83
Total Safety Inventory 921.43

Safety Inventory = Safety Factor (𝒛)×Standard Deviation of

Demand
Safety Inventory = NORMSINV (Service Level)×SD of
Demand
Aggregation – Safety Stock
Safety Inventory = Safety Factor (𝒛)×SD of Aggregated Demand

SD of Aggregated Demand = 𝝈𝟏 𝟐 + 𝝈𝟐 𝟐 + … + 𝝈𝒏 𝟐

= 232 + 852 + 672 + 542 + 342 + 452 +

642 + 932 + 382 + 542 + 882 + 742

= 220.60

Safety Stock = 1.2816 × 220.60 = 282.71

921.44 −282.71
Percentage Reduction = × 100 = 69.32 %
921.44
Aggregation – Safety Stock
Warehous Markets Mean SD of
e Demand Demand
Delhi Chandigarh 𝜇1 = 100 𝜎1 = 23
Delhi 𝜇2 = 345 𝜎2 =85
Kanpur 𝜇4 = 154 𝜎4 = 54
Mumbai Ahmedabad 𝜇3 = 267 𝜎3 = 67
Bhopal 𝜇6 = 212 𝜎6 = 45
Mumbai 𝜇8 = 387 𝜎8 = 93
Kolkata Guwahati 𝜇5 = 121 𝜎5 = 34
Kolkata 𝜇7 = 285 𝜎7 = 64
Bhubaneswar 𝜇9 = 201 𝜎9 = 38
Bangalore Hyderabad 𝜇10 = 254 𝜎10 = 54
Bangalore 𝜇11 = 323 𝜎11 = 88
Chennai 𝜇12 = 276 𝜎12 = 74
Aggregation – Safety Stock
 Models of Aggregation

• Information centralization

• Specialization

• Product substitution

• Component commonality

• Postponement

11-23
 Information Centralization
• Virtual aggregation

• Information system that allows access to current

inventory records in all warehouses from each warehouse

• Most orders are filled from closest warehouse

• In case of a stockout, another warehouse can fill the order

• Better responsiveness, lower transportation cost, higher

product availability, but reduced safety inventory
 Specialization
• Stock all items in each location or stock different
items at different locations?
– Different products may have different demands in different
locations (e.g., snow shovels)
– There can be benefits from aggregation

• Benefits of aggregation can be affected by:

– coefficient of variation of demand (higher cv yields greater
reduction in safety inventory from centralization)

– value of item (high value items provide more benefits from

centralization)
EXERCISE 8
Gap has started selling through its online channel along with its retail stores. Management
has to decide which products to carry at the retail stores and which products to carry at
a central warehouse to be sold only via the online channel. Gap currently has 900 retail
stores in the United States. Weekly demand for size large Khaki pants at each store is
normally distributed, with a mean of 800 and a standard deviation of 100. Each pair of
pants costs $30. Weekly demand for purple cashmere sweaters at each store is normally
distributed, with a mean of 50 and a standard deviation of 50. Each sweater costs $100.
Gap has a holding cost of 25 percent. Gap manages all inventories using a continuous
review policy, and the supply lead time for both products is four weeks. The targeted CSL
is 95 percent.

How much reduction in holding cost per unit sold can Gap expect on moving each of the
two products from the stores to the online channel?

Which of the two products should Gap carry at the stores, and which should it carry at
the central warehouse for the online channel? Why? Assume demand from one week to
the next week to be independent.
 Large Khaki Cashmere
Product Pants Product Sweaters
Mean Weekly Demand, D 800 Mean Weekly Demand, D 50
Standard Deviation of Weekly Demand 100 Standard Deviation of Weekly Demand 50
Replenishment Lead Time, L 4 Replenishment Lead Time, L 4
Lead time Demand, DL 3200 Lead time Demand, DL 200
SD of Lead Time Demand 200 SD of Lead Time Demand 100
Cycle Service Level 95.00% Cycle Service Level 95.00%

Safety Stock (=ROP-DL) 328.97 Safety Stock (=ROP-DL) 164.49

Reorder Point 3528.97 Reorder Point 364.49

Price 30 Price 100

Holding cost 25% Holding cost 25%

Total Safety Stock at 900 retail stores 296073.65 Total Safety Stock at 900 retail stores 148036.89
Total Inventory at 900 retail stores 3176073.65 Total Inventory at 900 retail stores 328036.84

Aggregation Aggregation
Aggregated Weekly Demand 720000 Aggregated Weekly Demand 45000
SD of aggregated weekly demand 3000 SD of aggregated weekly demand 1500
Replenishment Lead Time, L 4 Replenishment Lead Time, L 4
Lead time Demand, DL 2880000 Lead time Demand, DL 180000
SD of Lead Time Demand 6000 SD of Lead Time Demand 3000
Cycle Service Level 95.00% Cycle Service Level 95.00%

Safety Stock (=ROP-DL) 9869.121762 Safety Stock (=ROP-DL) 4934.560881

Reorder Point 2889869.122 Reorder Point 184934.56

Benefit of Aggregation (Inventory Units) 286204.5311 Benefit of Aggregation (Inventory Units) 143102.2655
Benefit of Aggregation ($) $21,46,533.98 Benefit of Aggregation ($) $35,77,556.64
0.97 0.97
POSTPONEMENT

• Delay of product differentiation until closer to sale

• Aggregation of forecasts prior to differentiation

• Individual forecasts are required close to the time of sale and therefore
greater forecast accuracy

• Matching demand and supply

• There is a cost associated with postponement, however

POSTPONEMENT

• Postponement allows a firm to increase profits and better match supply

and demand

• Postponement may reduce overall profits for a firm if a single product

contributes the majority of the demand

• Tailored Postponement
– Used for a part of the demand
– Used for the portion of the demand that is certain
– Benetton uses both Option 1 & 2: 800 units of each color & 1550
(postponement)
A large fraction of Benetton’s sales are from knit garments in solid colors
(four). Starting with thread, there are two steps to completing the garment –
dying and knitting. Traditionally thread was dyed and then garment was
knitted (Option1). Benetton developed a procedure where dying was
postponed until after the garment was knitted (Option 2).

Benetton sells each knit garment at a retail price 𝑝 = $50. Option 1 results
in a manufacturing cost of $20, whereas Option 2 results in a
manufacturing cost of $22 per garment. Benetton disposes of any unsold
garments at the end of the season in a clearance for 𝑠 = $10 each. The
knitting and manufacturing process takes a total of twenty weeks. Benetton
sells garments in four colors. Twenty weeks in advance, Benetton forecasts
demand for each color to be normally distributed with a mean of 𝜇 = 1000
and a standard deviation of 𝜎 = 500 . Demand for each color is
independent. Quantify the impact of postponement for Benetton.
 Reduce Forecast Errors
• Improved forecasting
– Through better market intelligence and collaboration

• Quick Response
– Reduce lead time and multiple orders

• Aggregation of Demand
– Postponement - Postpone product differentiation

•Tailored Sourcing
– Use responsive supplier as backup

• Information Sharing

• Collaborative Forecasting and Planning

• Single Stage of Control