US 11,869,008 B2
Minimizing risks posed to online services
Nghiem Le, Sherman Oaks, CA (US); Leandro Alves, Coral Springs, FL (US); Nikolas Terani, Moorpark, CA (US); Eugene Bendersky, Reseda, CA (US); and Taylor Cressy, West Hills, CA (US)
Assigned to Intuit Inc., Mountain View, CA (US)
Filed by Intuit Inc., Mountain View, CA (US)
Filed on Oct. 29, 2021, as Appl. No. 17/515,327.
Prior Publication US 2023/0134689 A1, May 4, 2023
Int. Cl. G06Q 20/40 (2012.01); G06Q 20/24 (2012.01)
CPC G06Q 20/4016 (2013.01) [G06Q 20/24 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for selectively advancing funds based on risks posed by transactions associated with an online service, the method performed by one or more processors of a system coupled to the online service and comprising:
receiving, for each of a plurality of transactions, a request for payment of the transaction between a vendor and a consumer;
sending, for each of the plurality of transactions, a first request to a database associated with the online service for historical transactions and personal attributes of the vendor concurrently with sending a second request to a number of third-party services for credit information and personal attributes of the consumer;
receiving, for each of the plurality of transactions, information responsive to the first and second requests from the database and the third-party services, respectively;
aggregating, for each of the plurality of transactions, the historical transactions and personal attributes of the vendor with the credit information and personal attributes of the consumer into a respective structured data set;
combining a plurality of structured data sets corresponding to the plurality of transactions into a single thread;
concurrently obtaining a respective risk score for each of the plurality of transactions based on an application of one or more risk assessment rules to the single thread by a machine learning model trained with at least the historical transactions and the personal attributes of at least one vendor associated with the plurality of transactions and the credit information of at least one consumer associated with the plurality of transactions and the at least one vendor associated with the plurality of transactions;
determining, for each of the plurality of transactions, whether or not to advance funds to the vendor for the transaction, prior to sending a payment request to a financial service designated by the consumer, based at least in part on the respective risk score; and
training the machine learning model with at least a plurality of pairs of structured data sets and risk scores, each pair comprising the structured data set and the risk score for a respective transaction of the plurality of transactions.