# US 2018/0025296 A1 · Linear Regression Modeling For Load Factors

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0025296 A1
- Document ID: US20180025296A1
- Status: Published application
- Kind: A1
- Application number: 15/695,446
- Filed: 2017-09-05
- Published: 2018-01-25
- Earliest claimed: 2011-11-17
- Assignees: American Airlines, Inc.
- Applicants: American Airlines, Inc.
- Inventors: James Fox; Randeep Ramamurthy; Julianne Anderson; Arthur Busse; Marcial Lapp; Daniel Muzich; Thomas Trenga
- Web page: https://patentgrep.com/patent/US20180025296A1

## CPC

- G06Q 10/02: Reservations, e.g. for tickets, services or events
- G06Q 10/022: {Reservation systems with overbooking processing}
- G06Q 10/0283: {for travel seating}
- G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/0872: {using inventory planning}
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system for linear regression modeling for load factors is disclosed. The system determines capacity, optimal authorizations, probabilities and models using a real-time iterative process throughout a period of time.

## Claims

### Claim 1

A system comprising:
a network interface in communication with a memory;
the memory in communication with a processor;
the processor, when executing a computer program, executes operations comprising:
determining, by an optimizer module in communication with the processor, a capacity (CAP) from an airline central data repository;
forecasting, by the processor and in real-time iteratively throughout a period of time, a no-show forecast (NSF) based on passenger name record characteristics from a passenger system;
determining, by the optimizer module in communication with the processor and using a flight cost prediction model in a forecaster module and in real-time iteratively throughout the period of time, an optimal booking authorization level (AU) that minimizes an overbooking cost,
determining, by a cost engine in communication with the processor and in real-time iteratively throughout the period of time, a spoiled seat (SS) cost;
determining, by the cost engine in communication with the processor and in real-time iteratively throughout the period of time, a denied boarding (DB) cost based on a probability of a volunteer not taking the flight;
wherein the overbooking cost is based upon the CAP, the NSF, the SScost and the DB cost,
wherein the DB cost is based on actual passengers booked, market load factors, accommodations cost and a probability a denied boarding will result in a voucher, and
wherein the DB cost is dynamically calculated based upon a plurality of forecasts for a re-accommodation cost for each of a plurality of denied passengers for the flight;
wherein the DB cost is determined by:
DB costi=DDBi*[(1−ncf)*(voucher_amt*b*pvi+(ill_will+exp_invol_costi)*(1−pvi)+HMTi)];
where,
DB costi is DB cost of the ith passenger who is denied boarding;
ncf is no Compensation Factor, the percentage of DBs that do not qualify to be compensated due to non-compliance, 0≦ncf≦1;
voucher_amt is the actual amount of the voucher offered to passengers who volunteer to DB;
b is a breakage factor, the expected percentage of voucher dollars that will be used, 0≦b≦1;
given i DBs, pvi is the expected percentage of volunteers, calculated from a linear regression model using historical data, 0≦pv≦1;
ill_will is the extra cost added due to bad customer image and possible loss of customers due to involuntarily denying boarding to passengers;
exp_invol_costi is the expected payout to an involuntary DB passenger;
HMTi is the expected hotel, meal and transportations costs of the ith DB passenger, based on the time to accommodate the passenger; and,
DDBi is a double DB factor, increases the DB cost based on the probability that this DB causes another DB, wherein DDBi increases depending on the load factor of an entire directional market and the station load factor for that day, and wherein DDBi≧1.
modeling, by the cost engine in communication with the processor and in real-time iteratively throughout the period of time, DB cost as an aggregate, for each passenger denied boarding, of a breakage adjusted voucher cost, an involuntary rate draft cost, a rolling denied boarding marginal cost and a secondary accommodations cost;
updating, by the processor and on a database and in real-time iteratively throughout the period of time, an authorization parameter to create an updated authorization parameter for the flight based upon the AU to maximize revenue for the flight and minimize the costs of overbooking;
providing, by the processor and to a revenue management system and in real-time iteratively throughout the period of time, the updated authorization parameter,
wherein the updated authorization parameter impacts the revenue management system and a reservation system,
wherein the revenue management system determines, based on the updated authorization parameter, a number of additional seats to be sold for the flight and a respective price for each additional seat,
wherein the revenue management system transmits to the reservation system the number of additional seats to be sold for the flight and the respective price for each additional seat;
creating, by the processor and in real-time, a voucher for the number of additional seats for the flight, wherein the voucher changes throughout the day based on the updating the updated authorization parameter and most current conditions to minimize costs; and
providing, by the processor and in real-time and to a customer mobile device, the voucher for the number of additional seats for the flight.

### Claim 2 (depends on 1)

The system of claim 1, further comprising:
providing, by the processor, a certain number of updated tickets to access the flight;
providing access information, by the processor and to an airline kiosk, that allows access to the flight to certain passengers with the updated tickets,
wherein the airline kiosk provides an updated boarding passes with machine readable data to the passengers;
receiving, by the processor and from an airport scanner, scanned data from the updated tickets, wherein access to the airplane is provided in response to the airport scanner scanning the machine readable data on the updated tickets and verifying the machine readable data on the updated tickets;
providing denial information, by the processor, that denies access to the flight to denied passengers with the updated tickets; and
compensating, by the processor, the denied passengers.

### Claim 3 (depends on 1)

The system of claim 1, the operations further comprising determining the DB cost for a plurality of booking authorization levels (AUs).

### Claim 4 (depends on 3)

The system of claim 3, wherein the determining the DB cost for the plurality of AUs comprises determining for each of the plurality of AUs a forecasted number of denied passengers for the flight.

### Claim 5 (depends on 4)

The system of claim 4, the operations further comprising analyzing a plurality of flights in an airline network to identify a plurality of alternate accommodation (AA) flights, wherein each AA flight in the plurality of AA flights covers at least a same directional market as the flight.

### Claim 6 (depends on 5)

The system of claim 5, wherein the determining the re-accommodation cost comprises analyzing booking information for the plurality of AA flights.

### Claim 7 (depends on 6)

The system of claim 6, the operations further comprising selecting for a first denied passenger a first AA flight from the plurality of AA flights, wherein the first denied passenger is one of the plurality of denied passengers.

### Claim 8 (depends on 7)

The system of claim 7, the operations further comprising, selecting for a second denied passenger and based upon the selecting the first AA flight for the first denied passenger, a second AA flight from the plurality of AA flights, wherein the second denied passenger is one of the plurality of denied passengers and the second AA flight is one of the plurality of AA flights.

### Claim 9 (depends on 8)

The system of claim 8, the operations further comprising, in response to the second AA flight being scheduled to depart on a different day than the flight, adding an accommodations cost to the DB cost associated with the second denied passenger.

### Claim 10 (depends on 9)

The system of claim 9, further comprising:
storing, by the processor, the updated authorization parameter in the database;
tuning, by the processor, the database to optimize database performance,
wherein the tuning includes placing frequently used files as indexes on separate file systems to reduce in and out bottlenecks;
designating, by the processor, a key field in data tables to speed searching for the updated authorization parameter;
sorting, by the processor, the updated authorization parameter according to a known order to simplify the lookup process;
obtaining, by the processor, the updated authorization parameter from the database.

### Claim 11 (depends on 4)

The system of claim 4, wherein the determining the forecasted number of denied passengers for the flight comprises determining based upon at least two of the CAP, the AU and the NSF.

### Claim 12 (depends on 11)

The system of claim 11, wherein the determining the forecasted number of denied passengers for the flight determining based upon at least one of a binomial distribution, a poisson distribution and a normal approximation of a binomial distribution.

### Claim 13

A system, comprising:
a network interface communicating with a memory;
the memory communicating with a processor;
the processor, when executing a computer program, executes operations comprising:
determining, by an optimizer module in communication with the processor, a capacity (CAP) from an airline central data repository;
forecasting, by the processor and in real-time iteratively throughout a period of time, a no-show forecast (NSF) based on passenger name record characteristics from a passenger system;
determining, by the optimizer module in communication with the processor and using a flight cost prediction model in a forecaster module and in real-time iteratively throughout the period of time, an optimal booking authorization level (AU) that minimizes an overbooking cost,
determining, by a cost engine in communication with the processor and in real-time iteratively throughout the period of time, a spoiled seat (SS) cost;
determining, by the cost engine in communication with the processor and in real-time iteratively throughout the period of time, a denied boarding (DB) cost based on a probability of a volunteer not taking the flight;
wherein the overbooking cost is based upon the CAP, the NSF, the SScost and the DB cost,
wherein the DB cost is based on actual passengers booked, market load factors, accommodations cost and a probability a denied boarding will result in a voucher, and
wherein the DB cost is dynamically calculated based upon a plurality of forecasts for a re-accommodation cost for each of a plurality of denied passengers for the flight;
wherein the DB cost is determined by:
DB costi=DDBi*[(1−ncf)*(voucher_amt*b*pvi+(ill_will+exp_invol_costi)*(1−pvi)+HMTi)];
where,
DB costi is DB cost of the ith passenger who is denied boarding;
ncf is no Compensation Factor, the percentage of DBs that do not qualify to be compensated due to non-compliance, 0≦ncf≦1;
voucher_amt is the actual amount of the voucher offered to passengers who volunteer to DB;
b is a breakage factor, the expected percentage of voucher dollars that will be used, 0≦b≦1;
given i DBs, pvi is the expected percentage of volunteers, calculated from a linear regression model using historical data, 0≦pv≦1;
ill_will is the extra cost added due to bad customer image and possible loss of customers due to involuntarily denying boarding to passengers;
exp_invol_costi is the expected payout to an involuntary DB passenger;
HMTi is the expected hotel, meal and transportations costs of the ith DB passenger, based on the time to accommodate the passenger; and,
DDBi is a double DB factor, increases the DB cost based on the probability that this DB causes another DB, wherein DDBi increases depending on the load factor of an entire directional market and the station load factor for that day, and wherein DDBi>1.
modeling, by the cost engine in communication with the processor and in real-time iteratively throughout the period of time, DB cost as an aggregate, for each passenger denied boarding, of a breakage adjusted voucher cost, an involuntary rate draft cost, a rolling denied boarding marginal cost and a secondary accommodations cost;
updating, by the processor and on a database and in real-time iteratively throughout the period of time, an authorization parameter to create an updated authorization parameter for the flight based upon the AU to maximize revenue for the flight and minimize the costs of overbooking;
providing, by the processor and to a revenue management system and in real-time iteratively throughout the period of time, the updated authorization parameter,
wherein the updated authorization parameter impacts the revenue management system and a reservation system,
wherein the revenue management system determines, based on the updated authorization parameter, a number of additional seats to be sold for the flight and a respective price for each additional seat,
wherein the revenue management system transmits to the reservation system the number of additional seats to be sold for the flight and the respective price for each additional seat.
creating, by the processor and in real-time, a voucher for the number of additional seats for the flight, wherein the voucher changes throughout the day based on the updating the updated authorization parameter and most current conditions to minimize costs; and
providing, by the processor and in real-time and to a customer mobile device, the voucher for the number of additional seats for the flight.

### Claim 14 (depends on 13)

The system of claim 13, the operations further comprising:
analyzing a plurality of flights in an airline network to identify a plurality of alternate accommodation (AA) flights, wherein each AA flight the plurality of AA flights covers at least a same directional market as the flight; and
determining the re-accommodation cost by analyzing booking information for the plurality of AA flights.

### Claim 15 (depends on 14)

The system of claim 14, the operations further comprising:
selecting for a passengeri an AA flightj from the plurality of AA flights; and
assigning passengeri to AA flightj, wherein j is a member of (1 . . . J) flights, wherein J=the total number of the plurality of AA flights, wherein i is a member of (1 . . . I) passengers, and wherein I=the total number of the plurality of denied passengers for the flight.

### Claim 16 (depends on 15)

The system of claim 15, the operations further comprising:
selecting, for a passengeri+1 and based upon the assigning passengeri to AA flightj, an AA flightj+1 from the plurality of AA flights; and
assigning passengeri+1 to AA flightj+1.

### Claim 17 (depends on 16)

The system of claim 16, wherein AA flightj and AA flightj+1 are the same flight.

### Claim 18 (depends on 13)

The system of claim 13, the operations further comprising determining the No-Show-Rate by:
determining a booked passenger no-show forecast (NSF) for each booked passenger on the flight, wherein the booked passenger NSF is a based upon whether the respective booked passenger flew on a previous leg of a passenger itinerary;
accumulating each respective booked passenger NSF to determine a booked passenger NSF for the flight;
aggregating, by the processor, the booked passenger NSF for the flight and an unbooked passenger NSF to create a flight NSF; and
calculating No-Show-Rate=(1−flight NSF).

### Claim 19

A computer-based method for determining an authorization level (AU) for a flight, the method comprising:
obtaining, by the processor, a capacity (CAP) and a no-show forecast (NSF) for a flight;
determining, by the processor, an optimal booking authorization level (AU) that minimizes an overbooking cost,
wherein the overbooking cost is based upon the CAP, the NSF, a spoiled seat (SS) cost and a denied boarding (DB) cost,
wherein the DB cost is dynamically calculated based upon a plurality of forecasts for a re-accommodation cost for each of a plurality of denied passengers for the flight; and
updating, by the processor and on a database, an authorization parameter for the flight based upon the AU.