US 12,218,926 B2
Time constrained electronic request evaluation
Vishal Sood, Bangalore (IN); Yegya Narayanan Gopala Krishnan, Chennai (IN); Sudhindra Murthy, Bangalore (IN); Vidya Sagar Durga, Bangalore (IN); and Chirag Gupta, Bangalore (IN)
Assigned to PayPal, Inc., San Jose, CA (US)
Filed by PayPal, Inc., San Jose, CA (US)
Filed on Aug. 11, 2021, as Appl. No. 17/399,300.
Claims priority of application No. 202141029163 (IN), filed on Jun. 29, 2021.
Prior Publication US 2022/0417229 A1, Dec. 29, 2022
Int. Cl. G06N 20/00 (2019.01); H04L 9/40 (2022.01); H04L 29/06 (2006.01)
CPC H04L 63/08 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a server computer system from a computing device, a request submitted via a user account, the request including a first set of characteristics associated with the request;
executing, by the server computer system, a first machine-learning based model to determine a first risk score for the request, wherein the first risk score is determined by inputting the first set of characteristics into the first machine-learning based model;
sending, by the server computer system to the computing device, an initial authentication decision for the request, wherein the initial authentication decision is generated based on the first risk score;
executing, by the server computer system after sending the initial authentication decision, a second, different machine-learning based model to determine a second risk score for the request, wherein the second risk score is determined by inputting the first set of characteristics and a second, different set of characteristics associated with the user account into the second machine-learning based model;
storing, by the server computer system in a key-value store, the second risk score with a corresponding session identifier (ID) as a key in the key-value store; and
determining, by the server computer system based on the second risk score, a final authentication decision.