公开(公告)号：US20230186083A1

公开(公告)日：2023-06-15

申请号：US17987737

申请日：2022-11-15

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Alain Briancon ,  Gregory Klose ,  Michael Wegan ,  Lee Harper ,  Andrew Kraemer ,  Arun Prakash

IPC: G06N3/08 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/044 ,  G06N3/045

Abstract: Provided is a process, including: obtaining a first training dataset of subject-entity records; training a first machine-learning model on the first training dataset; forming virtual subject-entity records by appending members of a set of candidate action sequences to time-series of at least some of the subject-entity records; forming a second training dataset by labeling the virtual subject-entity records with predictions of the first machine-learning model; and training a second machine-learning model on the second training dataset.

公开(公告)号：US20220014504A1

公开(公告)日：2022-01-13

申请号：US17362775

申请日：2021-06-29

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Jean Belanger ,  Karen Bennet ,  Michael L. Roberts ,  Jay M. Williams

IPC: H04L29/06 ,  G06F21/62 ,  G06F21/60

Abstract: Disclosed herein are methods, systems, and processes for distributed logging for securing non-repudiable transactions. Credentials, request information, response information, and action items generated and received by a requesting computing system and a responding computing system, and transmitted between the requesting computing system and the responding computing system are separately recorded and stored in a requestor log maintained by the requesting computing system and in a responder log maintained by the responding computing system.

公开(公告)号：US20230141553A1

公开(公告)日：2023-05-11

申请号：US17945876

申请日：2022-09-15

Applicant: Cerebri AI Inc.

Inventor： Jean Belanger ,  Michael L. Roberts ,  Gabriel M. Silberman ,  Karen Bennet

IPC: G06Q30/0201 ,  G06Q10/067 ,  G06N20/00 ,  G06F18/2321 ,  G06F18/2415 ,  G06N7/01 ,  G06N5/025

CPC classification number: G06Q30/0201 ,  G06Q10/067 ,  G06N20/00 ,  G06F18/2321 ,  G06F18/24155 ,  G06N7/01 ,  G06N5/025 ,  G06F8/35

Abstract: In some implementations, an event timeline that includes one or more interactions between a customer and a supplier may be determined. A starting value may be assigned to individual events in the event timeline. A sub-sequence comprising a portion of the event timeline that includes at least one reference event may be selected. A classifier may be used to determine a previous relative value for a previous event that occurred before the reference event and to determine a next relative value for a next event that occurred after the reference event until all events in the event timeline have been processed. The events in the event timeline may be traversed and a monetized value index assigned to individual events in the event timeline.

公开(公告)号：US20230085451A1

公开(公告)日：2023-03-16

申请号：US17887344

申请日：2022-08-12

Applicant: Cerebri AI Inc.

Inventor： Jean Belanger ,  Alain Briancon ,  James Stojanov ,  Gabriel M. Silberman

IPC: G06Q40/02 ,  G06N20/00 ,  G06N7/00

Abstract: Provided is process, including: obtaining interaction-event records; determining, based on at least some of the interaction-event records, sets of event-risk scores, wherein: at least some respective event-risk scores are indicative of an effective of a respective risk ascribed by a first entity to a respective aspect of a second entity; and at least some respective event-risk scores are based on both: respective contributions of respective corresponding events to a subsequent event, and a risk ascribed to a subsequent event; and storing the sets of event-risk scores in memory.

公开(公告)号：US11082409B2

公开(公告)日：2021-08-03

申请号：US16656074

申请日：2019-10-17

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Jean Belanger ,  Karen Bennet ,  Michael L. Roberts ,  Jay M. Williams

IPC: G06F21/00 ,  H04L29/06 ,  G06F21/62 ,  G06F21/60

Abstract: Disclosed herein are methods, systems, and processes for distributed logging for securing non-repudiable transactions. Credentials, request information, response information, and action items generated and received by a requesting computing system and a responding computing system, and transmitted between the requesting computing system and the responding computing system are separately recorded and stored in a requestor log maintained by the requesting computing system and in a responder log maintained by the responding computing system.

公开(公告)号：US20210056569A1

公开(公告)日：2021-02-25

申请号：US17009482

申请日：2020-09-01

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Michael Louis Roberts ,  Jean Belanger ,  Karen Bennet

IPC: G06Q30/02 ,  G06Q10/06 ,  G06N20/00 ,  G06K9/62 ,  G06N5/02 ,  G06N7/00

Abstract: In some implementations, a computing device determines an event timeline that comprises one or more finance-related events associated with a person. A production classifier may be used to determine (i) an individual contribution of each event in the event timeline to a financial capacity of the person and (ii) a first decision regarding whether to extend credit to the person. A bias monitoring classifier may, based on the event timeline, determine a second decision whether to extend credit to the person. The bias monitoring classifier may be trained using pseudo-unbiased data. If a difference between the first decision and the second decision satisfies a threshold, the production classifier may be modified to reduce bias in decisions made by the production classifier.

公开(公告)号：US20200067888A1

公开(公告)日：2020-02-27

申请号：US16656074

申请日：2019-10-17

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Jean Belanger ,  Karen Bennet ,  Michael L. Roberts ,  Jay M. Williams

IPC: H04L29/06 ,  G06F21/62 ,  G06F21/60

Abstract: Disclosed herein are methods, systems, and processes for distributed logging for securing non-repudiable transactions. Credentials, request information, response information, and action items generated and received by a requesting computing system and a responding computing system, and transmitted between the requesting computing system and the responding computing system are separately recorded and stored in a requestor log maintained by the requesting computing system and in a responder log maintained by the responding computing system.

公开(公告)号：US11941691B2

公开(公告)日：2024-03-26

申请号：US17887344

申请日：2022-08-12

Applicant: Cerebri AI Inc.

Inventor： Jean Belanger ,  Alain Briancon ,  James Stojanov ,  Gabriel M. Silberman

IPC: G06Q40/03 ,  G06N7/01 ,  G06N20/00

CPC classification number: G06Q40/03 ,  G06N7/01 ,  G06N20/00

Abstract: Provided is process, including: obtaining interaction-event records; determining, based on at least some of the interaction-event records, sets of event-risk scores, wherein: at least some respective event-risk scores are indicative of an effective of a respective risk ascribed by a first entity to a respective aspect of a second entity; and at least some respective event-risk scores are based on both: respective contributions of respective corresponding events to a subsequent event, and a risk ascribed to a subsequent event; and storing the sets of event-risk scores in memory.

公开(公告)号：US11922435B2

公开(公告)日：2024-03-05

申请号：US17009482

申请日：2020-09-01

Applicant: Cerebri AI Inc.

Inventor： Gabriel M. Silberman ,  Michael Louis Roberts ,  Jean Belanger ,  Karen Bennet

IPC: G06N20/00 ,  G06F18/2321 ,  G06F18/2415 ,  G06N5/025 ,  G06N7/01 ,  G06Q10/067 ,  G06Q30/0201 ,  G06F8/35

CPC classification number: G06Q30/0201 ,  G06F18/2321 ,  G06F18/24155 ,  G06N5/025 ,  G06N7/01 ,  G06N20/00 ,  G06Q10/067 ,  G06F8/35

Abstract: In some implementations, a computing device determines an event timeline that comprises one or more finance-related events associated with a person. A production classifier may be used to determine (i) an individual contribution of each event in the event timeline to a financial capacity of the person and (ii) a first decision regarding whether to extend credit to the person. A bias monitoring classifier may, based on the event timeline, determine a second decision whether to extend credit to the person. The bias monitoring classifier may be trained using pseudo-unbiased data. If a difference between the first decision and the second decision satisfies a threshold, the production classifier may be modified to reduce bias in decisions made by the production classifier.

公开(公告)号：US11900397B2

公开(公告)日：2024-02-13

申请号：US17945876

申请日：2022-09-15

Applicant: Cerebri AI Inc.

Inventor： Jean Belanger ,  Michael L. Roberts ,  Gabriel M. Silberman ,  Karen Bennet

IPC: G06Q30/0201 ,  G06Q10/067 ,  G06N20/00 ,  G06F18/2321 ,  G06F18/2415 ,  G06N7/01 ,  G06N5/025 ,  G06F8/35

CPC classification number: G06Q30/0201 ,  G06F18/2321 ,  G06F18/24155 ,  G06N5/025 ,  G06N7/01 ,  G06N20/00 ,  G06Q10/067 ,  G06F8/35

Abstract: In some implementations, an event timeline that includes one or more interactions between a customer and a supplier may be determined. A starting value may be assigned to individual events in the event timeline. A sub-sequence comprising a portion of the event timeline that includes at least one reference event may be selected. A classifier may be used to determine a previous relative value for a previous event that occurred before the reference event and to determine a next relative value for a next event that occurred after the reference event until all events in the event timeline have been processed. The events in the event timeline may be traversed and a monetized value index assigned to individual events in the event timeline.