公开(公告)号：US20240355091A1

公开(公告)日：2024-10-24

申请号：US18600349

申请日：2024-03-08

申请人： Capital One Services, LLC

发明人： Mark IBRAHIM ,  John PAISLEY ,  Ceena MODARRES ,  Melissa LOUIE

IPC分类号： G06V10/762 ,  G06F18/23213 ,  G06N3/04 ,  G06N3/084

CPC分类号： G06V10/763 ,  G06F18/23213 ,  G06N3/04 ,  G06N3/084

摘要： Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.

公开(公告)号：US20230267332A1

公开(公告)日：2023-08-24

申请号：US17990050

申请日：2022-11-18

申请人： Capital One Services, LLC

发明人： Mark IBRAHIM ,  John PAISLEY ,  Ceena MODARRES ,  Melissa LOUIE

IPC分类号： G06N3/084 ,  G06N3/04 ,  G06V10/762 ,  G06F18/23213

CPC分类号： G06N3/084 ,  G06N3/04 ,  G06V10/763 ,  G06F18/23213

摘要： Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.

公开(公告)号：US20210241115A1

公开(公告)日：2021-08-05

申请号：US16855685

申请日：2020-04-22

申请人： Capital One Services, LLC

发明人： Mark IBRAHIM ,  John PAISLEY ,  Ceena MODARRES ,  Melissa LOUIE

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06K9/62

摘要： Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.