10.

7 Periodic Review
Model with
Probabilistic Demand
 The order-quantity, reorder point inventory models previously
discussed require a continuous review inventory system. In a
continuous review inventory system, the inventory position is
monitored continuously so that an order can be placed whenever the
recorder point is reached. Computerized inventory systems can easily
provide continuous reviews required by order-quantity, reorder point
models.
An alternative to the continuous review system is the periodic
review inventory system. With a periodic review inventory system, the
inventory is checked and recording is done only a specified points in
time. For example, inventory may be checked and orders placed on
weekly, biweekly, monthly, or some other periodic basis.
 When a firm or business handles multiple products, the
periodic review system offers the advantage of requiring that orders
for several items be placed at the same preset periodic review time.
With this type of inventory system, the shipping and inventory of
of orders for multiple products are easily coordinated. Under the
previously discussed order-quantity, reorder point system, the
reorder points for various products can be encountered at
substantially different points in time, making the coordination of
orders for multiple products more difficult.
 To illustrate this system, let us consider Dollar Discounts, a
firm with several retail stores that carry a wide variety of products for
households use. The company operates its inventory system with a
two-week periodic review. Under this system, a retail store manager
may order any number of units of any product from the Dollar
Discounts central warehouse every two weeks. Orders for all products
going to a particular store are combined into one shipment. When
making the order quantity decision for each product cannot be made
until the next review period.
Assuming that the lead time is less than the length of the
review period, an order placed at a review period will be received
prior to the next review period. In this case, the how-much-to-order
decision at any review is determined using the following:
 Because the demand is probabilistic, the inventory on hand at the
review period, H, will vary. Thus, the order quantity that must be
sufficient to bring the inventory position back to its maximum or
replenishment level M can be expected to vary each period.
For example, if the replenishment level for a particular product is 50
units and the inventory on hand at the review period is H = 12 units, an
order of
Q = M - H = 50 - 12 = 38 units should be made.
Thus, under the periodic review model, enough units are ordered each
review period to bring the the inventory position back up to the
replenishment level.
 A typical inventory pattern for periodic review model with
probabilistic demand is shown in Figure 10.13. Note that the time
between periodic reviews is predetermined and fixed. The order
quantity Q at each review period can vary and is shown to be the
difference between the replenishment level and the inventory on
hand. Finally, as with other probabilistic models, an unusually high
demand can result in an occasional stock-out.
 The decision variable in the periodic review model is the
replenishment level M. To determine M, we could begin by developing a
total cost model, including holding, ordering, and stock-out costs.
Instead, we describe an approach that is often used in practice. In this
approach, the objective is to determine a replenishment level that will
meet a desired performance level, such as reasonably low probability
of stock-out or a reasonably low number of stock-out per year.
 In the Dollar Discounts problem, we assume that management’s
objective is to determine the replenishment level with only a 1%
chance of a stock-out. In the periodic review model, the order quantity
at each review period must be sufficient to cover demand for the
review plus the demand for the following lead time. Suppose that the
order is to be placed at the time t. To determine this order quantity,
we must realize that the quantity ordered at the time t must last until
the next time inventory is replenished, which will be time (t + review
period + lead time).
 Thus, the total length of the time that the order quantity at time t must
last is equal to the review period plus the lead time.
Figure 10.14 shows the normal probability distributions of demand
during the review period plus the lead-time period for one of the Dollar
Discounts

The mean is 250 units and the standard deviation of demand is 45 units.
Given this situation, the logic used to establish M is similar to the logic
used to establish the reorder point in Section 10.6.
Figure 10.15 shows the replenishment level M with a 1% chance that
demand will exceed the replenishment level. In other words, Figure
10.15 shows the replenishment level that allows a 1% chance of a
stock-out associated with the replenishment decision. Using the
normal probability distribution table in Appendix B, we see that 1 -
0.01 = 0.99 of the area in the left tail of the normal probability
distribution occurs at z = 2.33 standard deviations above the mean.
Therefore, for the assumed normal probability distribution with
and , the replenishment level is determined by
Although other probability distributions can be used to express the
demand during the review period plus the lead-time period, if the normal
probability distribution is used, the general expression for M is

Where z is the number of standard deviations necessary to obtain the

acceptable stock-out probability.
If the demand had been deterministic rather than probabilistic, the
replenishment level would have been the demand during the review
period plus the demand during the lead-time period. In this case, the
replenishment level would have been 250 units, and no stock-out would
have occured. However, with the probabilistic demand, we have seen that
higher inventory is necessary to allow for uncertain demand and to control
the probability of a stock-out. In the Dollar discount problem, 355 - 250 =
105 is the safety stock that is necessary to absorb any higher-than-usual
demand during the review period plus the demand during the lead-time
period. This safety stock limits the probability of a stock-out to 1%.
More Complex Periodic
Review Models
More complex versions of the periodic review model incorporate a reorder
point as another decision variable; that is, instead of ordering at every periodic
review, a reorder point is established. If inventory on hand at the periodic
review is at or below the reorder point, a decision is made to order up to the
replenishment level. However, if the inventory on hand at the periodic review is
greater than the reorder level, such an order is not placed, and the system
continues until the next periodic review. In this case, the cost of ordering is a
relevant cost and can be reached based on minimizing the expected total cost.
Situations with lead times longer than the review period add to the complexity
of the model. The mathematical level required to treat these more extensive
periodic review models is beyond the scope of this text.
THANK YOU