Chapter 2

Inventory Management Click to edit and Risk Pooling

Master subtitle style

McGraw-Hill/Irwin

Copyright 2008 by The McGraw-Hill Companies, Inc. All rights reserved.

1-1

CASE: Steel Works

l l l l l l

Background of case and intent Overview of business What does data tell you about Specialty? How much inventory might you expect? What opportunities are there for Custom? Wrap up

Stephen C. Graves Copyright 2003 All Rights Reserved

1-2

Background & Intent

l l

Abstraction from summer consulting job Intent is to examine a realistic, but simplified inventory context and perform a diagnosis of problem poor service and too much inventory

Stephen C. Graves Copyright 2003 All Rights Reserved

1-3

Custom Products
l l l l l l

Rapid growth, 1/3 of total sales ($133 MM) One customer per product Very high margins High service level 3 plants, co-located with R&D center Each product produced at a single plant

Stephen C. Graves Copyright 2003 All Rights Reserved

1-4

Specialty Products
l l l l l l l

Rapid growth, 2/3 of total sales ($267 MM) 6 product families 3 plants, each producing 2 product families 130 customers, 120 products Few big customers Highly volatile demand High service level

Stephen C. Graves Copyright 2003 All Rights Reserved

1-5

Consultant Recommendation
l l l

Drop low volume products Improve forecasts Consolidate warehouses

Stephen C. Graves Copyright 2003 All Rights Reserved

1-6

What Does Data Tell You?

DB R10 DB R12 DB R15 DF R10 DF R12 DF R15 DF R23 15.5 1008 2464 97 18.5 55 35.5 13.2 256 494 92.5 11.4 80 45.9 cv 0.85 0.25 0.20 0.95 0.62 1.46 1.29
1-7

Stephen C. Graves Copyright 2003 All Rights Reserved

What Does Data Tell You?

l l

Durabend R12:
l

One customer accounts for 97% of demand High volume (2) is not very volatile Low volume (5) is very volatile

7 products:
l l

Stephen C. Graves Copyright 2003 All Rights Reserved

1-8

How Much Inventory Should You Expect?

l l l

Assume base stock model with periodic review Review period = r = ? Lead time = L = ?

E [ I ] = r + z r + L 2
Stephen C. Graves Copyright 2003 All Rights Reserved
1-9


DB R10 DB R12 DB R15 DF R10 DF R12 DF R15 DF R23 15.5 1008 2464 97 18.5 55 35.5

13.2 256 494 92.5 11.4 80 45.9

Cycle stock
8 504 1232 49 9 28 18 1848

Saf. Stock
26 510 990 185 23 160 92 1986

E[I]
34 1014 2222 234 32 188 110 3834

Act. Inv.
72 740 1875 604 55 388 190 3824

S
Assumes r = 1; L=0.25; and z = 1.8 Cycle stock = r /2

Safety stock = z r+L

Stephen C. Graves Copyright 2003 All Rights Reserved
1-10

What Are the Opportunities at Custom?

l l l

Combine production and inventory for common items, e. g. DF R23 Produce monthly: reduce setups by half and pool safety stocks Produce twice a month: same number of setups but cut cycle stock and review period in half

Stephen C. Graves Copyright 2003 All Rights Reserved

1-11

Wrap Up
l l l

Realistic diagnostic exercise In real life: not as clean, more data and more considerations Yet simple models and principles can provide valuable guidance

Stephen C. Graves Copyright 2003 All Rights Reserved

1-12

2.1 Introduction Why Is Inventory Important?

Distribution and inventory (logistics) costs are quite substantial
Total U.S. Manufacturing Inventories ($m): l 1992-01-31: $m 808,773 l 1996-08-31: $m 1,000,774 l 2006-05-31: $m 1,324,108 Inventory-Sales Ratio (U.S. Manufacturers): l 1992-01-01: 1.56 l 2006-05-01: 1.25
1-13

Why Is Inventory Important?

l

GMs production and distribution network

l l l l

20,000 supplier plants 133 parts plants 31 assembly plants 11,000 dealers

l l l l

Freight transportation costs: $4.1 billion (60% for material shipments) GM inventory valued at $7.4 billion (70%WIP; Rest Finished Vehicles) Decision tool to reduce:
l l l

combined corporate cost of inventory and transportation. Shipment sizes (inventory policy) Routes (transportation strategy)

26% annual cost reduction by adjusting:

1-14

Why Is Inventory Required?

l

Uncertainty in customer demand

l l

Shorter product lifecycles More competing products Quality/Quantity/Costs/Delivery Times

l l l

Uncertainty in supplies
l

Delivery lead times Incentives for larger shipments

1-15

Holding the right amount at the right time is difficult!

l

Dell Computers was sharply off in its forecast of demand, resulting in inventory write-downs
l

1993 stock plunge

Liz Claibornes higher-than-anticipated excess inventories

l

1993 unexpected earnings decline, 1994 shortages in the ThinkPad line 2001 $ 2.25B excess inventory charge

l l

IBMs ineffective inventory management

l l

Ciscos declining sales

1-16

Inventory Management-Demand Forecasts

l

Uncertain demand makes demand forecast critical for inventory related decisions:
l l l

What to order? When to order? How much is the optimal order quantity? INVENTORY POLICY!!

Approach includes a set of techniques

l

1-17

Supply Chain Factors in Inventory Policy

l l l l l

Estimation of customer demand Replenishment lead time The number of different products being considered The length of the planning horizon Costs
l

Order cost:
l l

Product cost Transportation cost State taxes, property taxes, and insurance on inventories Maintenance costs Obsolescence cost Opportunity costs

Inventory holding cost, or inventory carrying cost:

l l l l

Service level requirements

1-18

2.2 Single Stage Inventory Control

l l

Single supply chain stage Variety of techniques

l l l l l l l

Economic Lot Size Model Single Period Models Multiple Order Opportunities Continuous Review Policy Variable Lead Times Periodic Review Policy Service Level Optimization

1-19

Economic Lot Size Model

FIGURE 2-3: Inventory level as a function of time

1-20

Assumptions
D items per day: Constant demand rate l Q items per order: Order quantities are fixed, i.e., each time the warehouse places an order, it is for Q items. l K, fixed setup cost, incurred every time the warehouse places an order. l h, inventory carrying cost accrued per unit held in inventory per day that the unit is held (also known as, holding cost) l Lead time = 0 (the time that elapses between the placement of an order and its receipt) l Initial inventory = 0 l Planning horizon is long (infinite).
l

1-21

Deriving EOQ
l l l l

Total cost at every cycle: Average inventory holding cost in a cycle: Q/2 Cycle time T =Q/D K D h Q + Average total cost per unit Q time:2
Q =
*

hQ T K + 2

2 KD h
1-22

EOQ: Costs

FIGURE 2-4: Economic lot size model: total cost per unit time

1-23

Single Period Models

Short lifecycle products l One ordering opportunity only l Order quantity to be decided before demand occurs
l l

Order Quantity > Demand => Dispose excess inventory Order Quantity < Demand => Lose sales/profits

1-24

Single Period Models

l

Using historical data

l l

identify a variety of demand scenarios determine probability each of these scenarios will occur determine the profit associated with a particular scenario given a specific order quantity
l l

Given a specific inventory policy

l l

weight each scenarios profit by the likelihood that it will occur determine the average, or expected, profit for a particular ordering quantity.

Order the quantity that maximizes the average profit.

1-25

Single Period Model Example

FIGURE 2-5: Probabilistic forecast

1-26

Additional Information
l l l l

Fixed production cost: $100,000 Variable production cost per unit: $80. During the summer season, selling price: $125 per unit. Salvage value: Any swimsuit not sold during the summer season is sold to a discount store for $20.

1-27

Two Scenarios
Manufacturer produces 10,000 units while demand ends at 12,000 swimsuits Profit = 125(10,000) - 80(10,000) - 100,000 = $350,000 l Manufacturer produces 10,000 units while demand ends at 8,000 swimsuits Profit = 125(8,000) + 20(2,000) - 80(10,000) 100,000 = $140,000
l

1-28

Relationship Between Optimal Quantity and Average Demand

l

Compare marginal profit of selling an additional unit and marginal cost of not selling an additional unit Marginal profit/unit = Selling Price - Variable Ordering (or, Production) Cost Marginal cost/unit = Variable Ordering (or, Production) Cost - Salvage Value If Marginal Profit > Marginal Cost => Optimal Quantity > Average Demand If Marginal Profit < Marginal Cost => Optimal Quantity < Average Demand

l l

1-29

For the Swimsuit Example

l l l l l

Average demand = 13,000 units. Optimal production quantity = 12,000 units. Marginal profit = $45 Marginal cost = $60.

Thus, Marginal Cost > Marginal Profit => optimal production quantity < average demand.

1-30

Multiple Order Opportunities

REASONS l To balance annual inventory holding costs and annual fixed order costs. l To satisfy demand occurring during lead time. l To protect against uncertainty in demand. TWO POLICIES l Continuous review policy
l l l

inventory is reviewed continuously an order is placed when the inventory reaches a particular level or reorder point. inventory can be continuously reviewed (computerized inventory systems are used)

Periodic review policy

l l l

inventory is reviewed at regular intervals appropriate quantity is ordered after each review. it is impossible or inconvenient to frequently review inventory and place orders if necessary.
1-31

Continuous Review Policy

l l

l l

Daily demand is random and follows a normal distribution. Every time the distributor places an order from the manufacturer, the distributor pays a fixed cost, K, plus an amount proportional to the quantity ordered. Inventory holding cost is charged per item per unit time. Inventory level is continuously reviewed, and if an order is placed, the order arrives after the appropriate lead time. If a customer order arrives when there is no inventory on hand to fill the order (i.e., when the distributor is stocked out), the order is lost. The distributor specifies a required service level.
1-32

Continuous Review Policy

l l l l l

AVG = Average daily demand faced by the distributor STD = Standard deviation of daily demand faced by the distributor L = Replenishment lead time from the supplier to the distributor in days h = Cost of holding one unit of the product for one day at the distributor = service level. This implies that the probability of stocking out is 1 -

1-33

Continuous Review Policy

l

(Q,R) policy whenever inventory level falls to a reorder level R, place an order for Q units What is the value of R?

1-34

Continuous Review Policy

l l l l

Average demand during lead time: L x AVG Safety stock: z STD L Reorder Level, R:
L AVG + z STD L
2 K AVG Q= h
1-35

Order Quantity, Q:

Service Level & Safety Factor, z

Service Level 90% 91% 92% 93% 94% 95% 96% 97% 98% 99% 99.9%

1.29

1.34

1.41

1.48

1.56

1.65

1.75

1.88

2.05

2.33

3.08

z is chosen from statistical tables to ensure that the probability of stockouts during lead time is exactly 1 -

1-36

Inventory Level Over Time

FIGURE 2-9: Inventory level as a function of time in a (Q,R) policy

Inventory level before receiving an order = z STD L Inventory level after receiving an order = Q + z STD L Average Inventory =
Q 2

+ z STD L
1-37

Continuous Review Policy Example

l l l l l l

A distributor of TV sets that orders from a manufacturer and sells to retailers Fixed ordering cost = $4,500 Cost of a TV set to the distributor = $250 Annual inventory holding cost = 18% of product cost Replenishment lead time = 2 weeks Expected service level = 97%

1-38

Continuous Review Policy Example

Month Sales Sept 200 Oct 152 Nov. 100 Dec. 221 Jan. 287 Feb. 176 Mar. 151 Apr. 198 May 246 June 309 July 98 Aug 156

Average monthly demand = 191.17 Standard deviation of monthly demand = 66.53 Average weekly demand = Average Monthly Demand/4.3 Standard deviation of weekly demand = Monthly standard deviation/4.3

1-39

Continuous Review Policy Example

Parameter Average weekly demand Standard deviation of weekly demand 32.08 Average demand during lead time 89.16 Safety stock Reorder point

Value

44.58

86.20

176

Weekly holding cost =

0.18 250 = 0.87 52

Optimal order quantity =

Q=

2 4,500 44.58 = 679 .87

Average inventory level = 679/2 + 86.20 = 426

1-40

Variable Lead Times

l l l

Average lead time, AVGL Standard deviation, STDL. Reorder Level, R:

R = AVG AVGL + z AVGL STD2 + AVG2 STDL2
Amount of safety stock= z AVGL STD2 + AVG 2 STDL2 Order Quantity =
Q= 2K A VG h
1-41

Periodic Review Policy

l l l

Inventory level is reviewed periodically at regular intervals An appropriate quantity is ordered after each review Two Cases:
l

Short Intervals (e.g. Daily)

l l l

Define two inventory levels s and S During each inventory review, if the inventory position falls below s, order enough to raise the inventory position to S. (s, S) policy May make sense to always order after an inventory level review. Determine a target inventory level, the base-stock level During each review period, the inventory position is reviewed Order enough to raise the inventory position to the base-stock level. Base-stock level policy

Longer Intervals (e.g. Weekly or Monthly)

l l l l l

1-42

(s,S) policy
l l l

Calculate the Q and R values as if this were a continuous review model Set s equal to R Set S equal to R+Q.

1-43

Base-Stock Level Policy

l l

Determine a target inventory level, the basestock level Each review period, review the inventory position is reviewed and order enough to raise the inventory position to the base-stock level Assume: r = length of the review period L = lead time AVG = average daily demand STD = standard deviation of this daily demand.

1-44

Base-Stock Level Policy

l

Average demand during an interval of r + L days=r + L) AVG ( Safety Stock=

z STD r + L

1-45

Base-Stock Level Policy

FIGURE 2-10: Inventory level as a function of time in a periodic review policy

1-46

Base-Stock Level Policy Example

l

Assume:
l l l

distributor places an order for TVs every 3 weeks Lead time is 2 weeks Base-stock level needs to cover 5 weeks

l l l l l

Average demand = 44.58 x 5 = 222.9 Safety stock = 1.9 32.8 5 Base-stock level = 223 + 136 = 359 Average inventory level = 344.58 + 1.9 32.08 5 = 203.17 2 Distributor keeps 5 (= 203.17/44.58) weeks of supply.

1-47

Service Level Optimization

l l

Optimal inventory policy assumes a specific service level target. What is the appropriate level of service?
l

May be determined by the downstream customer

l l

Retailer may require the supplier, to maintain a specific service level Supplier will use that target to manage its own inventory

Facility may have the flexibility to choose the appropriate level of service
1-48

Service Level Optimization

FIGURE 2-11: Service level inventory versus inventory level as a function of lead time

1-49

Trade-Offs
l

Everything else being equal:

l l

the higher the service level, the higher the inventory level. for the same inventory level, the longer the lead time to the facility, the lower the level of service provided by the facility. the lower the inventory level, the higher the impact of a unit of inventory on service level and hence on expected profit

1-50

Retail Strategy
l

Given a target service level across all products determine service level for each SKU so as to maximize expected profit. Everything else being equal, service level will be higher for products with:
l l l l

high profit margin high volume low variability short lead time

1-51

Profit Optimization and Service Level

FIGURE 2-12: Service level optimization by SKU

1-52

Profit Optimization and Service Level

l l

Target inventory level = 95% across all products. Service level > 99% for many products with high profit margin, high volume and low variability. Service level < 95% for products with low profit margin, low volume and high variability.

1-53

Risk Pooling
l l

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.

1-54

Demand Variation
l

Standard deviation measures how much demand tends to vary around the average
l

Gives an absolute measure of the variability

Coefficient of variation is the ratio of standard deviation to average demand

l

Gives a relative measure of the variability, relative to the average demand

1-55

Acme Risk Pooling Case

l l

l l l

Electronic equipment manufacturer and distributor 2 warehouses for distribution in New York and New Jersey (partitioning the northeast market into two regions) Customers (that is, retailers) receiving items from warehouses (each retailer is assigned a warehouse) Warehouses receive material from Chicago Current rule: 97 % service level Each warehouse operate to satisfy 97 % of demand (3 % probability of stock-out)
1-56

New Idea
l

l l

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.

1-57

Historical Data
PRODUCT A
Week Massachusetts New Jersey Total 1 33 46 79 2 45 35 80 3 37 41 78 4 38 40 78 5 55 26 81 6 30 48 78 7 18 18 36 8 58 55 113

PRODUCT B
Week Massachusetts New Jersey Total 1 0 2 2 2 3 4 6 3 3 3 3 4 0 0 0 5 0 3 3 6 1 1 2 7 3 0 3 8 0 0 0

1-58

Summary of Historical Data

Statistics Product Average Demand Standard Deviation Coefficient of of Demand Variation 13.2 1.36 12.0 1.58 20.71 1.9 0.34 1.21 0.31 1.26 0.27 0.81 Massachusetts Massachusetts New Jersey New Jersey Total Total A B A B A B 39.3 1.125 38.6 1.25 77.9 2.375

1-59

Inventory Levels
Product Average Demand During Lead Time 39.3 1.125 38.6 1.25 77.9 2.375 Safety Stock Reorder Point Q Massachusetts Massachusetts New Jersey New Jersey Total Total A B A B A B 25.08 2.58 22.8 3 39.35 3.61 65 4 62 5 118 6 132 25 31 24 186 33

1-60

Savings in Inventory
l

Average inventory for Product A:

l l l l

At NJ warehouse is about 88 units At MA warehouse is about 91 units In the centralized warehouse is about 132 units Average inventory reduced by about 36 percent At NJ warehouse is about 15 units At MA warehouse is about 14 units In the centralized warehouse is about 20 units Average inventory reduced by about 43 percent

Average inventory for Product B:

l l l l

1-61

Critical Points
l

The higher the coefficient of variation, the greater the benefit from risk pooling l 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 l 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
1-62