Escolar Documentos
Profissional Documentos
Cultura Documentos
by
Ronald H. Ballou
May, 1980
Abstract
-1-
li
-2-
level is usually not proportional to the number of stocking
points. For example, if sales are routed through 1/2 the number
of existing stocking points, the total inventory required may
drop by 1/3 of its previous level. This disproportionality is
accurate since rates are published for common carriers or, in the
case of private carriage, they can be determined through straight-
forward accounting practice. The inventory consolidation effects
- __ - _established
are _much inventory replenishment rules, and the execution of
these rules is highly individualized by company and by stockkeeping
overall
purposesinventory
since it levels would
replaces the be usefulive
alternat foritem-by-
planning and
item auditing
estimati ng
where:
mD.
1 is the amount of safety stodk in the ith stocking point, and
I
aD is the amount of regular stock in the ith stocking point.
form becomes a little trickier to curve fit and all terms usually
are not statistically significant. Consider the nature of one of
1 + Z.S 1
I
Di = demand throughput at warehouse i
sD = standard deviation of demand
IT -i=]N
a 1.
Thus, theoretically, we would expect total inventory to be a
fashion. For a number of.reasons, we will find that this does not
The benefit that the simple model has is that it can be struc-
tured from existing data that are readily available within most firms.
li
l
-6-
increased variability compared with the aggregated data.
500 -
1.)
400 -
Warehouse v) 4-
average
inventory
level,
000's lb.
300 -
200 - -
1
(i,
0
-5
_.-Ii »/-« 1 /8
I - . 6 Di.0.635
2
R = 0.8 2
-
1
«»
(:)
6.15)
0 ic/'4
-) I ':)4 C.' O
100 »« .
0 1 0
1
1 1 . 1 . 101 1
0 1 1
0 200 400 600 800 1000 1200 1400 1600
relationship of
0.68
I. = 0.311 D.
1 1 (5)
2
offered the best fit with an R = 0.83. The constant term was near-
ly zero and has been eliminated from the relationship. However , the
straightline relationship of
I. = 0.596+0.091 D. (6)
1 1
with an R2 = 0.76 was selected. The reason was that the constant
term in the equation better represented the high level of promotional
I, = 7,10 D. (7)
J J
-Dallas
400 -
0 plant
0- Phoenix
plant
300 -
Warehouse 1
average L_ 0.632
inventory, I. = 4.44 D.
11
000's lb.
2
200 - * R = 0.4 8
e
m0
100 -
0 0 Minneapolis
plant
0 1 .J 1
0 500 1000 1500
-- - ---.- .--.------- .Annual warehouse throughput,_ _SOO's__lb.
1
.. .. ..
I. = 0.59641 + 0.09055 D-
1
0.68
R2 = 0.76 0 0 Ii = 0.311579 D.1
R2 = 0.83
3 -.
m
Average
inventory
level »,
0
00,000'S)
2-
0 m .0
0 0 0
GA
.J
. .
El iIi]
0 0 1977 Data
0 21 1978 Data
1
-
E]
0 0 10 20
1 301 1 1 3 401 1 1 1
50
100
W 75
ehouse
average e
nlntory,
0*'s lb.
@
50 e
e
e
25 ® 0 90
Ii = 7.1 Di '
1 ee 0 2
e
o R = 0.64
%
01/0 9e
0o .e 0
/8 -lio. e
O .-#*- 1 * 1 1
- -0--- ---- -- ----. - 5--- - -- --- ..__ 10__ __ __ 15
li
.4
..
- 12 -
ship usually to range between 0.65 and 0.75 with a mean of about
0.7. Thus, depending on the nature of the inventory policy used,
of the fitted model compared with what the stated policy would
dictate requires careful consideration. Also why the exponent
on demand is not as low as the 0.5 that theory suggests is possible
The reasons for the exponent on demand being greater than the
Replacement r. 0.60
parts I =26.910.
i Mixed push-pull
T strategy NA 0.60
.. 0.78 NA 0.78
Candy I Unknown
T =98.91D.
products 10.65 NA 0.65
Unknown
IT=67.7ID.1
a
A relationship expressing the execution of the firm's inventory policy.
b
Competing divisions of same parent company except second division
makes substantial buys from foreign manufacturers.
C Statement of the firm's actual inventory policy.
Source: Various
facilitydistribution planning studies involving the DISPLAN
location model.
- 15 -
There are two primary uses that the model has in the strategic
of stocking points.
As an Audit Tool
the power function model can- provide the necessary insights that
the case does show the level of the accuracy that can be achieved.
As an Estimating Tool
The use of the model as a tool for estimating the overall in-
Accounting for all demand in this manner gives the overall inventory
level. The number of stocking points and, therefore, the demand on
each point may be changed and the inventory levels estimated again
in this manner to accomplish a sensitivity analysis.
- 18 - -
TABLE 2
(3)=(2)4(1)
(1) (2)
05
C. S D. D... I.
Product i d 1 1 1 a
§ 1 .10 25 2312a 48.08 578.83
b
12.0
aMonthly demand
\1 (2312) (5) 1
b + 1.65(25)\ (8/8)1 = 578.83 from
Example:Il =N 2(.20)(.10)
Equation 2.
C
- 20 -
Summary
haps more importantly, it has shown that for companies using a pull-
more directly to demand such that economies of scale are not present,
The data for the model are readily obtained from the normal
1 -I---
- 22 -
End Notes
3
William J. Baumol and Philip Wolfe, "A Warehouse-Location Problem,"
Operations Research, Vol. 6 (March-April, 1958), pp. 252-63, and
Robert G. Brown, Decision Rules for Inventory Management (New York:
Holt, Rinehart and Winston, 1967), p. 353.
i
- 23 -
APPENDIX
Regular Stock
Regular stock is that amount of inventory to meet average demand
over the period of time from one stock replenishment to the next.
Based on the Wilson EOQ formulation, regular stock in a warehouse
where
represents the average value for the product class, the total regular
If D.
1
is the total demand_(throughput) on warehouse i, then
n Sni r--
n ID (A. 3)
I CRS):
j=l J =3 i i, ,1 Ei ='121[(E '1 i
If all warehouses contain roughly the same number of items for a
: particular product class , the total regular stock equation can be
approximated as
IRSi. = a- (A.4)
Since various inventory policies can prevail besides the Wilson EOQ,
the above equation can more generally be represented as
Safety Stock
of the demand during lead time distribution. This has been shown
by Brown2 to be
SDDLT
- 222'
V= LTSD +d jSL T (A. 5)
when both lead time and demand are normally distributed; where
SDDLT standard deviation during lead time, units.
2
Robert G. Brown, Smoothing, Forecasting and Prediction of Discrete
Time Series (Englewood Cliffs, N.J.: Prentice-Hall, Inc., 1962),
pp. 366-367.
./ I.
- 25 -
bution curve representing the service level for item j, the safety
stock for all items in a warehouse is
n n 0.5
jil (ss)j -iil zj [LT(hd )2 + diSt ] (A. 7)
ISS.
1
= mDi (A. 9)
Note that if g is less than 1, the effect of safety stock will become
incorporated in the regular stock term.
Other Stocks
Additions may be made to inventories in the form of speculative
- can be represented by
n
(A. 10)
w =jll Tj
8
- 26 -
Conclusion
safety stocks, and other stocks. Hence, the total stock I.1 in
warehouse i is
I.
1
= other stock + safety stock + regular stock
+I
RS..
= w + Iss.11
b
= w + mD. + aD .. (A. 11)
11
warehouse throughput and inventory level data. The exact form of the
simplified equation for the inventory in a single warehouse accounts
for the fact that the Wilson EOQ model may not be used to set regular
stock levels, the lead time distribution may not be strictly normally