US 11,869,002 B2
Card authentication technique selection via machine learning
Aditya Jain, Morgan Hill, CA (US); Piyush Neupane, Hayward, CA (US); and Yogesh Krishna Kandlur, Fremont, CA (US)
Assigned to PayPal, Inc., San Jose, CA (US)
Filed by PayPal, Inc., San Jose, CA (US)
Filed on Oct. 28, 2021, as Appl. No. 17/513,144.
Prior Publication US 2023/0140792 A1, May 4, 2023
Int. Cl. G06Q 20/40 (2012.01); G06Q 20/34 (2012.01)
CPC G06Q 20/401 (2013.01) [G06Q 20/34 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor that executes computer-executable instructions stored in a computer-readable memory, which causes the processor to perform operations comprising:
receiving, by a processor, a training dataset, wherein the training dataset includes a set of training attribute vectors and a set of authentication technique annotations that respectively correspond to the set of training attribute vectors;
training, by the processor, a machine learning model to initialize a set of internal parameters, identify the training dataset, and feed the training dataset to the machine learning model to determine which type of authentication technique to apply to a financial payment card based on the set of training attribute vectors and the respectively corresponding set of authentication technique annotations;
producing a training output based on the set of internal parameters;
applying, by the processor, the set of internal parameters to the machine learning model;
accessing electronically, by the processor, an attribute vector associated with the financial payment card from a data structure;
determining, by the processor and via execution of the machine learning model, an output indicative of a probability of successfully authenticating the financial payment card based on the attribute vector and the training dataset;
determining, by the processor and the machine learning model, whether to authenticate the financial payment card with a zero-dollar authentication technique or a tokenization authentication technique, based on the attribute vector and the output;
executing, by the processor, the zero-dollar authentication technique with respect to the financial payment card, when the processor determines that the financial payment card should be authenticated with the zero-dollar authentication technique; and
executing, by the processor, the tokenization authentication technique with respect to the financial payment card, when the processor determines that the financial payment card should be authenticated with the tokenization authentication technique.