US 11,887,025 B1
Method to generate predicted variances of an operation based on data from one or more connected databases
James Fox, Phoenix, AZ (US); Randeep Ramamurthy, Phoenix, AZ (US); Julianne Anderson, Tempe, AZ (US); Arthur Busse, Tempe, AZ (US); Marcial Lapp, Ann Arbor, MI (US); Daniel Muzich, Phoenix, AZ (US); and Thomas Trenga, Mesa, AZ (US)
Assigned to AMERICAN AIRLINES, INC., Fort Worth, TX (US)
Filed by American Airlines, Inc., Fort Worth, TX (US)
Filed on Mar. 30, 2023, as Appl. No. 18/128,950.
Application 18/128,950 is a continuation of application No. 17/945,848, filed on Sep. 15, 2022, abandoned.
Application 17/945,848 is a continuation of application No. 16/907,623, filed on Jun. 22, 2020, abandoned.
Application 16/907,623 is a continuation of application No. 15/812,723, filed on Nov. 14, 2017, abandoned.
Application 15/812,723 is a continuation of application No. 15/695,446, filed on Sep. 5, 2017, abandoned.
Application 15/695,446 is a continuation of application No. 14/038,278, filed on Sep. 26, 2013, abandoned.
Application 14/038,278 is a continuation of application No. 13/352,667, filed on Jan. 18, 2012, granted, now 8,600,787, issued on Dec. 3, 2013.
Application 13/352,667 is a continuation of application No. 13/348,417, filed on Jan. 11, 2012, abandoned.
Claims priority of provisional application 61/561,245, filed on Nov. 17, 2011.
Int. Cl. G06Q 10/00 (2023.01); G06Q 30/00 (2023.01); G06Q 10/02 (2012.01); G06Q 30/0202 (2023.01); G06Q 50/30 (2012.01); G06Q 10/0637 (2023.01); G06Q 10/087 (2023.01)
CPC G06Q 10/02 (2013.01) [G06Q 10/0637 (2013.01); G06Q 10/087 (2013.01); G06Q 30/0202 (2013.01); G06Q 50/30 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
predicting, by a processor, a spoiled value comprising a spoiled seat (SS) cost for each passenger location in a plurality of passenger locations associated with an operation comprising a flight;
predicting, by the processor, a denied value comprising a denied boarding (DB) cost for the operation based on a probability of a volunteer not taking the flight;
determining, by the processor in real-time iteratively, a passenger no-show prediction for each passenger booked for the operation, wherein the passenger no-show prediction is based upon whether the respective passenger flew on a previous leg of a passenger flight itinerary;
storing, by the processor and in one or more connected databases, the spoiled value, the denied value, and the passenger no-show prediction;
using, by the processor, a key field in pre-selected at least one of databases or data sectors to speed searches;
conducting, by the processor, sequential searches through all tables and files to speed the searches;
sorting, by the processor, records in a file according to a known order to simplify lookup;
completing, by the processor, a database merge function by using the key field;
tuning, by the processor, the one or more connected databases to optimize database performance, wherein the tuning comprises placing frequently used files on separate file systems to reduce in and out bottlenecks; and
obtaining, by the computer-based system, the spoiled value, the denied value, and the passenger no-show prediction from the one or more connected databases;
aggregating, by the processor in real-time iteratively, the passenger no-show prediction and an unbooked passenger attendance prediction to create an overall flight prediction; and
determining, by the processor, an authorized passenger location for the operation that minimizes an overfilled value, wherein the overfilled value is based upon an accumulation of each spoiled value, the denied value and the overall flight prediction.