Professional Documents
Culture Documents
Testing Theories of Price Dispersion and Scarcity Pricing in The Airline Industry
Testing Theories of Price Dispersion and Scarcity Pricing in The Airline Industry
$248
$368
500
2500
$490
7
14
Days Purchased in Advance
Roundtrip Fare
Average Fare
21
1000
7
14
Days Purchased in Advance
Roundtrip Fare
Average Fare
21
Outline
1)
Overview of theory
2)
Data
3)
Tests
Tests turn on comparing pricing in high
demand versus low demand flights
Evidence supports some scarcity pricing
Stronger evidence that ticket
characteristics drive price dispersion
4)
Scarcity pricing
MC of capacity = $20
Competitive Eqbm:
Offer X tickets at $20
Zero
On peak flights
Near departure
4)
Consumers learn
if prefer peak flight
Flights
Occur
Our
Data
Origin-Destination
Carrier
Fare
Flight no.
Coupon level class of service
Dates: Purchase, Departure, and Return
Data (continued)
.001
.002
.003
.004
.005
500
1000
Roundtrip Fare
Unmatched Transactions
1500
2000
Matched Transactions
Fare
Carrier
Route
Flight number
Flight dates (departure
and return)
Calculated average
load factor
At departure
At date of purchase
Ticket characteristics
Refundability
Travel restrictions
(e.g. day of week,
length of stay)
Stay restrictions
(e.g. minimum or
max stay)
Booking class
Saturday stay-over
Round trip and direct
1 sd
= .045*.34 1 sd
= 1.5%
= 2.3%
1 sd
= .045*.34
= 1.5%
1 sd
= 2.3%
Illustration of Mismeasurement
of Load Factor
Consider
120
100
100 seat
plane with 75
passengers
Suppose our CRS has
1/3 market share
Simulate observing
each ticket w/
pr=1/3, and scaling
up our observed #
tickets by 3
80
60
40
20
0
20
40
60
80
100
Our Measure of Load Factor
120
140
Attenuation Bias in
Load Factor Coefficient?
Use
( X ' X N ) 1 X ' y
Density
4
Median = 0.84
Mean = 0.78
.2
.4
.6
.8
R2 of log fares on dummy variables for bins
40
10
Density
20
30
Median = 0.028
Mean = 0.043
-.1
0
.1
.2
.3
Coefficient of Actual Load Factor Averaged Across Flight Segments
Predictions on Price
Dispersion
Predictions on Price
Dispersion
Predictions on Price
Dispersion
Fully Refundable
Few if any restrictions
Mean fare = $631
26% of tickets
Nonrefundable, but
No travel or stay restrictions
Mean fare = $440
32% of tickets
Nonrefundable
Travel and/or stay restrictions
Mean fare = $281
42% of tickets
Dana
Dana
27%
27%
32%
29%
35%
31%
36%
32%
17%
15%
44%
40%
Thought experiment
For a ticket bought 7 days before departure, if the plane is 10% fuller than
normal (for a plane 7 days before departure), what % more expensive is
the fare?
-.2
.2
Last 7 Days
-1
-.5
0
Load Factor's Pct Deviation
American
Continental
Northwest
.5
Delta
United
USAir
-.2
.2
Last 3 Days
-1
-.5
0
Load Factor's Pct Deviation
American
Continental
Northwest
.5
Delta
United
USAir
.5
.45
1
1.5
2
Variance of Arrival Rate
2.5
.65
Dispersion in Fares
As Approach Departure
7
14
Days Purchased in Advance
21
Kernel Regression
.4
.6
.8
Flight's Load Factor
1.2
Much
Interpretation
Actual
airline decision is a
complex OR problem
To solve the system-wide yield-management problem
would require approximately 250 million decision variables.
Because this mathematical programming formulation is
intractable, American Airlines Decision Technologies has
developed a series of operations research models. These
models effectively reduce the large problem to three much
smaller and far more manageable subproblems while still
realistically modeling the real-world situation.
Barry
The End
Matching Procedure
Match
-1
Fare's % Deviation
0
1
Last 7 Days
-1
-.5
0
.5
1
Load Factor's % Deviation for Day in Advance
Fare's % Deviation
1.5