US 11,893,633 B2
Adjustment of card configurations for flight interruptions
Jennifer Kwok, New York, NY (US); Daniel Miller, Astoria, NY (US); Lisa Guo, Herndon, VA (US); Xiaoguang Zhu, Great Neck, NY (US); Alexander Lin, Arlington, VA (US); Vyjayanthi Vadrevu, Pflugerville, TX (US); and Cameron Noah, Bethesda, MD (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 17, 2021, as Appl. No. 17/404,629.
Prior Publication US 2023/0055897 A1, Feb. 23, 2023
Int. Cl. G06Q 40/03 (2023.01); G06Q 50/30 (2012.01); G06Q 30/01 (2023.01); G06Q 20/40 (2012.01)
CPC G06Q 40/03 (2023.01) [G06Q 20/4015 (2020.05); G06Q 30/01 (2013.01); G06Q 50/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a computing device, past flight interruption data indicating a plurality of past flight interruptions;
receiving user transaction data indicating card transactions, which were performed during past flight interruptions, associated with a plurality of users;
training, by the computing device and based on the past flight interruption data and the user transaction data, a machine learning model to predict user spending configurations to be applied, during flight interruptions, to a card associated with a user, wherein the trained machine learning model is configured to generate a predicted user spending configuration based on input historical records for the user;
determining, by the computing device and based on the flight interruption data and the user transaction data, one or more historical records for the user of the plurality of users, wherein each record of the one or more historical records for the user indicates a past flight interruption and one or more performed card transactions associated with the past flight interruption, wherein the one or more performed card transactions were performed via the card associated with the user;
detecting a current flight interruption associated with the user;
determining, using the machine learning model and based on the detected current flight interruption and the one or more historical records for the user, one or more predicted user spending configurations to be applied during the current flight interruption to the card associated with the user; and
updating, based on the one or more predicted user spending configurations, one or more user spending configurations of the card associated with the user.