公开(公告)号：WO2023287970A1

公开(公告)日：2023-01-19

申请号：PCT/US2022/037106

申请日：2022-07-14

申请人： VISA INTERNATIONAL SERVICE ASSOCIATION

发明人： WANG, Sheng ,  CAI, Yiwei ,  KAN, Xi ,  YANG, Pei ,  WU, Peng

IPC分类号： G06N3/08

摘要： Provided is a system for segmenting large scale datasets according to machine learning models based on transfer learning that includes at least one processor programmed or configured to train a base machine learning model using a training dataset to generate a trained machine learning model, evaluate the trained machine learning model using an evaluation dataset, wherein, when evaluating the trained machine learning model using the evaluation dataset, the at least one processor is programmed or configured to generate a confidence score for each data instance of the evaluation dataset with the trained machine learning model, augment the evaluation dataset based on the confidence score for each data instance of the evaluation dataset to generate an augmented evaluation dataset, and retrain the trained machine learning model using the augmented evaluation dataset to generate a final machine learning model. Methods and computer program products are also provided.

公开(公告)号：WO2023014567A1

公开(公告)日：2023-02-09

申请号：PCT/US2022/038630

申请日：2022-07-28

申请人： VISA INTERNATIONAL SERVICE ASSOCIATION

发明人： WANG, Fei ,  CAI, Yiwei ,  WANG, Lan ,  LIN, Yu-San ,  WU, Yuhang ,  WANG, Sheng ,  CHEN, Qingguo

IPC分类号： G06Q20/40 ,  G06Q20/00 ,  G06Q20/36 ,  G06Q30/00 ,  G06Q40/00 ,  G06Q40/08

摘要： Provided is a system, method, and computer program product for a framework for monitoring acquirer credit settlement risk. A system for monitoring acquirer credit settlement risk includes a transaction database and at least one processor. The processor may be programmed or configured to generate a first acquirer risk score based on a plurality of transaction records and a first risk algorithm, a first merchant risk score based on the plurality of transaction records and the first risk algorithm, a second acquirer risk score based on the plurality of transaction records and a second risk algorithm, and a second merchant risk score based on the plurality of transaction records and the second risk algorithm. A final acquirer risk score may be generated based on the first acquirer risk score, the second acquirer risk score, the first merchant risk score, and the second merchant risk score.