	US 12,141,807 B2
	Method and system for assessing the reputation of a merchant
Liang Wang, Palo Alto, CA (US); Dhruv Gelda, Palo Alto, CA (US); Robert Christensen, Palo Alto, CA (US); Wei Zhang, Palo Alto, CA (US); Hao Yang, Palo Alto, CA (US); and Yan Zheng, Palo Alto, CA (US)
Assigned to Visa International Service Association, San Francisco, CA (US)
Appl. No. 17/763,255
Filed by VISA INTERNATIONAL SERVICE ASSOCIATION, San Francisco, CA (US)
PCT Filed Oct. 31, 2019, PCT No. PCT/US2019/059058 § 371(c)(1), (2) Date Mar. 24, 2022, PCT Pub. No. WO2021/086365, PCT Pub. Date Jun. 5, 2021.
Prior Publication US 2022/0366421 A1, Nov. 17, 2022
Int. Cl. G06Q 20/40 (2012.01); G06Q 30/018 (2023.01)

CPC G06Q 20/4016 (2013.01) [G06Q 30/0185 (2013.01)]

20 Claims

1. A computer implemented method for real-time determination of a merchant risk level, the method comprising:

calculating, with a transaction risk model of a transaction analysis system, a transaction risk score for each transaction that occurs at a merchant during an hour h, wherein h is from 1 to 24, wherein the transaction risk score is a continuous score, and wherein the transaction risk model comprises at least one of a Gradient Boosting Machine model or a Recurrent Neural Network model;

aggregating the transaction risk scores for each transaction that occurs at the merchant during hour h to obtain a merchant risk score m_hfor the merchant during each hour h;

repeating the calculating step and the aggregating step for each hour h;

compiling the merchant risk scores m_hto calculate a daily merchant risk score s_i;

providing the daily merchant risk score s_ito the merchant.