Yield Management

1. Ski resort
A ski resort is planning a year end promotion by offering a weekend special for $159 per
person based on double occupancy. The high season rate for these rooms, which
includes lift tickets, normally is $299. Management wants to hold some rooms for late
arrivals who are willing to pay the season rate. If the promotion of skiers who are willing
to pay full rate is approximately 20% and their average weekend demand has a normal
distribution with a mean of 50 and a standard deviation of 10, how many rooms should
be set aside for full-paying skiers?
Solution
𝐹−𝐷 299 − 159
𝑃(𝑑<𝑥) ≤ ≤ ≤ 0.58
𝜌∗𝐹 0.8 ∗ 299
Where:
x = seats reserved for full-fare passengers

d = demand for full-fare tickets

F = price of full-fare
D = price of discount fare
𝜌 = probability that a passenger is a shopper

Turning to areas of a standard normal distribution (Appendix A), the z value for a
cumulative probability of 0.58 is 0.02. Thus the number of rooms to protect for full-
paying skiers is 𝜇 + 𝑧 ∗ 𝜎 = 50 + (0.02) ∗ (10) = 52 rooms.
2. Town and Country
Town and Country has experienced a substantial increase in business volume because
of recent fare wars between the major air carriers. Town and Country operates a single
office at a major international airport, with a fleet of 60 compact and 30 midsize cars.
Recent developments have prompted management to rethink the company’s
reservation policy. The table below contains data on the rental experience of Town and
Country:
Car Rental Discount % Discount Daily Standard Fleet
Model Rate (F) Rate (D) Seekers (𝝆) Demand () Deviation () Size
Compact $30 $20 80 50 15 60
Midsize $45 $30 60 30 10 30

The daily demand appears to follow a normal distribution; however, it has been
observed that midsize-car customers do not choose to rent a compact when no midsize
car is available. The discount rate is available to persons who are willing to reserve a
car at least 14 days in advance and agree to pick up that car within 2 hours after their
flight arrives. Otherwise, a nonrefundable deposit against their credit card will be
forfeited. The current reservation policy is that 40 compact cars are held for customers
who are willing to pay the full rate and 25 midsize cars are held for full rate–paying
customers.
a) Using yield management, determine the optimal number of compact and midsize
cars to be held for customers paying the full rate.
b) Given your optimal reservation policy determined here, would you consider a
fleet expansion?
Solution
𝐹−𝐷
a) 𝑃(𝑑<𝑥) ≤ 𝜌∗𝐹

Where:
x = seats reserved for full-fare passengers

d = demand for full-fare tickets

F = price of full-fare
D = price of discount fare
𝜌 = probability that a passenger is a shopper
 𝐹−𝐷 30 − 20
𝑃(𝑑𝑐𝑜𝑚𝑝𝑎𝑐𝑡 <𝑥𝑐𝑜𝑚𝑝𝑎𝑐𝑡 ) ≤ ≤ ≤ 0.417
𝜌∗𝐹 30 ∗ 0.8
Turning to areas of a standard normal distribution (Appendix A), the z value for a
cumulative probability of 0.417 is 0.21.
Thus, 𝑥𝑐𝑜𝑚𝑝𝑎𝑐𝑡 = 𝜇 + 𝑧 ∗ 𝜎 = 50 − (0.21) ∗ (15) ≈ 46

𝐹−𝐷 45 − 30
𝑃(𝑑𝑚𝑖𝑑𝑠𝑖𝑧𝑒 <𝑥𝑚𝑖𝑑𝑠𝑖𝑧𝑒 ) ≤ ≤ ≤ 0.555
𝜌∗𝐹 45 ∗ 0.6
Turning to areas of a standard normal distribution (Appendix A), the z value for a
cumulative probability of 0.555 is 0.14.
Thus, 𝑥𝑚𝑖𝑑𝑠𝑖𝑧𝑒 = 𝜇 + 𝑧 ∗ 𝜎 = 30 − (0.14) ∗ (10) ≈ 31

b) Because the current fleet of midsize cars is smaller than the optimal number of
midsize cars that should be reserved for full-price paying customers, an
expansion of the midsize fleet should be considered.
 3. Blackjack Airline

During the recent economic slump, Blackjack

Airline discovered that airplanes on its Los
Angeles-to-Las Vegas route have been flying
with more empty seats than usual. To
stimulate demand, it has decided to offer a
special, non-refundable, 14-day advance-
purchase “gamblers fare” for only $49 one-
way based on a round-trip ticket. The regular
full-fare coach ticket costs $69 one-way. The
Boeing 737 used by Blackjack, has a capacity
95 in coach, and management wants to limit
the number of seats that are sold at the
discount fare in order to sell full-fare tickets to
passengers who have not made advance
travel plans. Considering recent experience,
the demand for full-fare tickets appears to
have a normal distribution, with a mean of 60
and a standard deviation of 15.

Calculate the number of full-fare seats to

reserve.

Solution
The yield management problem can be analysed with the critical fractile model used in
a previous seminar (overbooking problem).

𝐶𝑢
𝑃𝑐𝑟𝑖𝑡 =
𝐶𝑢 + 𝐶𝑜

Where:
x = seats reserved for full-fare passengers
d = demand for full-fare tickets
Cu = lost revenue associated with reserving too few seats at full fare (underestimate
demand). The lost opportunity is the difference between the fares ($69 - $49 = $20)
because we assume that the no shopper passenger, willing to pay full fare, purchased a
seat at the discount price
Co = cost of reserving one too many seats for sale at full fare (overestimated demand).
We assume that the empty full fare seat could have been sold at the discount price of
$49

𝐶𝑢 $20
𝑃(𝑑<𝑥) = = ≤ 0.29
𝐶𝑢 + 𝐶𝑜 $20 + $49

From Appendix A => z= -0.55

 Reserved full-fare seats = 𝜇 + 𝑧 ∗ 𝜎 = 60 + (−0.55) ∗ 15 = 51

The critical fractile model could be modified to account for the percentage of shoppers
(customers looking for a discount). The value for Co would now take two values
depending on the buying behavior of the passenger who would have purchased the
seat if not reserved for full fare. In our example,
$49 𝑖𝑓 𝑝𝑎𝑠𝑠𝑒𝑛𝑔𝑒𝑟 𝑖𝑠 𝑎 𝑠ℎ𝑜𝑝𝑝𝑒𝑟
𝐶𝑜 {
−($69 − $49) 𝑖𝑓 𝑝𝑎𝑠𝑠𝑒𝑛𝑔𝑒𝑟 𝑖𝑠 𝑎 𝑛𝑜𝑛𝑠ℎ𝑜𝑝𝑝𝑒𝑟
For the nonshopper case, the cost is reduced by the difference between the fares,
because the airline profits the nonshopper, who did not make purchase, paying the full
rather than the discount fare. To establish an expected value for Co, however, we need
the proportion 𝜌 of passengers who are shoppers. In this case, market research
determined that approximately 90 percent of passengers are discount seekers; thus, the
expected value for the cost of overage becomes
𝐶0 = (0.9) ∗ ($49) − (1 − 0.9) ∗ ($69 − $49) = $42.10
The critical fractile

𝐶𝑢 $20
𝑃(𝑑<𝑥) = = = 0.32
𝐶𝑢 + 𝐶𝑜 $20 + $42.10
From Appendix A => z= -0.47

 Reserved full-fare seats = 𝜇 + 𝑧 ∗ 𝜎 = 60 + (−0.47) ∗ 15 = 53

Substituting symbols for the values used in the example above, we can derive a simple
expression for determining the number of full-fare seats to reserved.
𝐹−𝐷
𝑃(𝑑<𝑥) =
𝜌∗𝐹

Where:
x = seats reserved for full-fare passengers
d = demand for full-fare tickets
F = price of full-fare
D = price of discount fare
𝜌 = probability that a passenger is a shopper

Note that having information of the percentage of shoppers has allowed us to reserve more full-
fare seats