Inventory Control

Models
Ch 5 (Uncertainty of Demand)
R. R. Lindeke
IE 3265, Production And
Operations Management
Lets do a ‘QUICK’ Exploration of
Stochastic Inventory Control (Ch 5)
 We will examine underlying ideas –
 We base our approaches on Probability Density
Functions (means & std. deviations)
 We are concerned with two competing ideas: Q
and R
 Q (as earlier) an order quantity and R a
stochastic estimate of reordering time and level
 Finally we are concerned with Servicing ideas –
how often can we supply vs. not supply a
demand (adds stockout costs to simple EOQ
models)
The Nature of Uncertainty
 Suppose that we represent demand as:
 D = Ddeterministic + Drandom
 If the random component is small compared to
the deterministic component, the models of
chapter 4 will be accurate. If not, randomness
must be explicitly accounted for in the model.
 In this chapter, assume that demand is a random
variable with cumulative probability distribution
F(t) and probability density function f(t).
Single Period Stochastic
Inventory Models
 These models have the objective of properly
balancing the cost of Underage – having not
ordered enough products vs. Overage – having
ordered more than we can sell
 These models apply to problems like:
 Planning initial shipments of ‘High-Fashion’ items
 Amount of perishable food products
 Item with short shelf life (like the daily newspaper)
 Because of this last problem type, this class of
problems is typically called the “Newsboy” problem
The Newsboy Model
 At the start of each day, a newsboy must decide
on the number of papers to purchase. Daily sales
cannot be predicted exactly, and are represented
by the random variable, D.
 The newsboy must carefully consider these
costs:
co = unit cost of overage
cu = unit cost of underage

 It can be shown that the optimal number of

papers to purchase is the fractile of the demand
distribution given by F(Q*) = cu / (cu + co).
Determination of the Optimal
Order Quantity for Newsboy Example
Computing the Critical Fractile:
 We wish to minimize competing costs (Co & Cu):
 G(Q,D) = Co*MAX(0, Q-D) + Cu*MAX(0, D-Q)
 D is actual (potential) Demand
 G(Q) = E(G(Q,D)) (an expected value)
 Therefore:
 
G (Q)  Co  MAX (0, Q  x) f  x dx  Cu  MAX (0, x  Q ) f  x dx
0 0
Q Q

G (Q)  Co   Q  x)  f  x  dx  Cu   x  Q )  f  x  dx
0 0

Here: f(x) is a probability density function

controlling the behavior of ordering
Applying Leibniz’s Rule:
 d(G(Q))/dQ = CoF(Q) – Cu(1 – F(Q))
 F(Q) is a cumulative Prob. Density Function
(as earlier – of the quantity ordered)
 Thus: G’(Q*) = (Cu)/(Co + Cu)
 This is the critical fractile for the order
variable as stated earlier
Lets see about this: Prob 5 pg 241
 Observed sales given as a number
purchased during a week (grouped)
 Lets assume some data was supplied:
 Make Cost: $1.25
 Selling Price: $3.50
 Salvageable Parts: $0.80
 Co = overage cost = $1.25 - $0.80 = $0.45
 Cu = underage cost = $3.50 - $1.25 = $2.25
Continuing:
 Compute Critical Ratio:
 CR = Cu/(Co + Cu) = 2.25/(.45 + 2.25) = .8333
 If we assume a continuous Probability Density
Function (lets choose a normal distribution):
 Z(CR)  0.967 when F(Z) = .8333 (from Std. Normal
Tables!)
 Z = (Q* - )/)
 From the problem data set, we compute
 Mean = 9856

 St.Dev. = 4813.5
Continuing:
 Q* = Z +  = 4813.5*.967 + 9856 = 14511
 Our best guess economic order quantity is
14511
 (We really should have done it as a Discrete
problem -- Taking this approach we would
find that Q* is only 12898)
Newsboy’s Extensions
 Assuming we have a certain number of parts
on hand, u > 0
 This extends the problem compared to our initial u = 0
assumption for the single period case
 This is true only if the product under study
has a shelf life that extends beyond one
period
 Here we still compute Q* will order only Q* - u
(or 0 if u > Q*)
Try one (in your Engineering Teams) :
 Do Problem 11a & 11b (pg 249)
Lot Size Reorder Point Systems
 Earlier we considered reorder points (number of
parts on hand when we placed an order) they
were dependent on lead times as a dependent
variable on Q, now we will consider R as an
independent variable just like Q
 Assumptions:
 Inventory levels are reviewed continuously (the level
of on-hand inventory is known at all times)
 Demand is random but the mean and variance of
demand are constant. (stationary demand)
Lot Size Reorder Point Systems
Additional Assumptions:
 There is a positive leadtime, τ. This is the time
that elapses from the time an order is placed
until it arrives.
 The costs are:
 Set-up cost each time an order is placed at $K per order
 Unit order cost at $C for each unit ordered
 Holding at $H per unit held per unit time (i.e., per year)
 Penalty cost of $P per unit of unsatisfied demand
Describing Demand
 The response time of the system (in this case) is the
time that elapses from the point an order is placed
until it arrives. Hence,
 The uncertainty that must be protected against is
the uncertainty of demand during the lead time.
 We assume that D represents the demand during
the lead time and has probability distribution F(t).
Although the theory applies to any form of F(t), we
assume that it follows a normal distribution for
calculation purposes.
Decision Variables
 For the basic EOQ model discussed in Chapter 4,
there was only the single decision variable Q.
 The value of the reorder level, R, was determined
by Q.
 Now we treat Q and R as independent decision
variables.
 Essentially, R is chosen to protect against
uncertainty of demand during the lead time, and Q
is chosen to balance the holding and set-up costs.
(Refer to Figure 5-5)
Changes in Inventory Over Time
for Continuous-Review (Q, R) System
The Cost Function
The average annual cost is given by:

G (Q, R)  h(Q / 2  R   )  K  / Q  p n( R) / Q
 Interpret n(R) as the expected number of stockouts per
cycle given by the loss integral formula (see Table A-4
(std. values)). And note, the last term is this cost model
is a shortage cost term
 The optimal values of (Q,R) that minimizes G(Q,R) can
be shown to be:
2 ( K  pn( R ))
Q
h
1  F ( R )  Qh / p
Solution Procedure
 The optimal solution procedure requires iterating
between the two equations for Q and R until
convergence occurs (which is generally quite fast)
 We consider that the problem has converged if 2
consecutive calculation of Q and R are within 1 unit
 A cost effective approximation is to set Q=EOQ
and find R from the second equation.
 A slightly better approximation is to set Q =
max(EOQ,σ)
 where σ is the standard deviation of lead time demand
when demand variance is high.
Ready to Try one? Lets!
 Try Problem 13a & 13b (pg 261)
 Start by computing EOQ and then begin
iterative solution for optimal Q and R values
Service Levels in (Q,R) Systems
 In many circumstances, the penalty cost, p, is
difficult to estimate. For this reason, it is
common business practice to set inventory
levels to meet a specified service objective
instead. The two most common service
objectives are:
1) Type 1 service: Choose R so that the probability of
not stocking out in the lead time is equal to a
specified value.
2) Type 2 service. Choose both Q and R so that the
proportion of demands satisfied from stock equals a
specified value.
Computations
 For type 1 service, if the desired service level
is α then one finds R from F(R)= α and
Q=EOQ.
 Type 2 service requires a complex interative
solution procedure to find the best Q and R.
However, setting Q=EOQ and finding R to
satisfy n(R) = (1-β)Q (which requires Table A-
4) will generally give good results.
Comparison of Service
Objectives
 Although the calculations are far easier for
type 1 service, type 2 service is generally the
accepted definition of service.
 Note that type 1 service might be referred to
as lead time service, and type 2 service is
generally referred to as the fill rate.
 Refer to the example in section 5-5 to see the
difference between these objectives in
practice (on the next slide).
Comparison (continued)
Order Cycle Demand Stock-Outs
1 180 0
2 75 0
3 235 45
4 140 0
5 180 0
6 200 10
7 150 0
8 90 0
9 160 0
10 40 0

 For a type 1 service objective there are two cycles out of ten in
which a stockout occurs, so the type 1 service level is 80%. For
type 2 service, there are a total of 1,450 units demand and 55
stockouts (which means that 1,395 demand are satisfied). This
translates to a 96% fill rate.
Example: Type 1 Service Pr 5-16
 Desire 95% Type I service Level
 F(R) = .95  Z is 1.645 (Table A4)
 From Problem 13:  was found to be 172.8
and  was 1400
 Therefore: R = Z +  = 172.8*1.645 + 1400
R = 1684.256  1685
 Use Q = EOQ = 1265
Example: Type 2 Service Pr 5-17
 Require Iterative Solution:
Q0  EOQ  1295
n( R1 )  1    * Q0  63.25

L  Z1  
n( R1 )
 63.25
 .3673
 172.8
 Z1  .065 & 1  F  R  =.474 from Table A4
2
 n( R1 ) 
Q1 
n( R1 )
   

2

1 F  R
EOQ
1  F  R  
 

 
2
Q1  63.25  1265  63.25
2
 1405
.474 .474
Example: Type 2 Service Pr 5-17
(cont.)
n  R2   1    Q1  .05*1405  70.25
L  Z 2   70.25  0.408
172.8
Z 2  0.02 & 1  F ( R2 )  0.508
R2   Z 2    1397

 
2
Q2  70.25  1265   70.25  1411
2
.508 .508
n  R3   0.05*1411  70.54
L  Z 3   70.54  0.4097
172.8
Z 3  .02
R3   Z 3    1397 SAME so Stop!
 Q, R  = 1411, 1397 
 (s, S) Policies
 The (Q,R) policy is appropriate when inventory levels
are reviewed continuously. In the case of periodic
review, a slight alteration of this policy is required.
Define two levels, s < S, and let u be the starting
inventory at the beginning of a period. Then

If u  s, order S  u
If u  s, don't order
(In general, computing the optimal values of s and S is much
more difficult than computing Q and R.)