公开(公告)号：US11816550B1

公开(公告)日：2023-11-14

申请号：US16933215

申请日：2020-07-20

Applicant: Amazon Technologies, Inc.

Inventor： Deepak Gupta ,  Anirban Majumder ,  Prateek Sircar ,  Rajeev Ramnarain Rastogi

IPC: G06N20/20 ,  G06N5/04 ,  G06N5/01

CPC classification number: G06N20/20 ,  G06N5/01 ,  G06N5/04

Abstract: Devices and techniques are generally described for generating confidence scores for boosting-based tree machine learning models. In various examples, a first record comprising a plurality of input variables may be received. In another example, a boosting-based tree machine learning model may generate, for the first record, a base model score. In various examples, the base model score may be generated based on the plurality of input variables and the base model score may represent a likelihood that the first record is associated with a first class. In some examples, a score confidence machine learning model may generate a confidence score for the first record. The confidence score may indicate a confidence in the base model score. In various examples, the first record may be processed based at least in part on the confidence score.

公开(公告)号：US11494686B1

公开(公告)日：2022-11-08

申请号：US15618519

申请日：2017-06-09

Applicant: Amazon Technologies, Inc.

Inventor： Prakash Mandayam Comar ,  Anirban Majumder ,  Srinivasan Hanumantha Rao Sengamedu

IPC: G06F15/18 ,  G06N20/00 ,  G06N5/04 ,  G06N3/00 ,  G06Q30/02

Abstract: At an artificial intelligence-based service, an indication of a similarity group of items of a data stream is obtained. A subset of the stream items is to be included in an ordered collection and presented via an interface which allows one or more types of interactions. Using a first data set which includes interaction records of items in the similarity group, one or more machine learning models are trained to predict a relevance metric associated with a particular type of interaction. A predicted value of the relevance metric is obtained from a trained version of a model and stored.

公开(公告)号：US10747400B1

公开(公告)日：2020-08-18

申请号：US15380259

申请日：2016-12-15

Applicant: Amazon Technologies, Inc.

Inventor： Anirban Majumder ,  Vinayak Shripad Puranik ,  Srinivasan Hanumantha Rao Sengamedu

IPC: G06F3/048 ,  G06F3/0482 ,  G06F16/248 ,  G06F16/2457

Abstract: The arrangement and selection of digital content to present to a user can be based at least in part upon the relevance of content, e.g., the probabilities of the user selecting to view more information and/or otherwise engaging with instances of the content. Features of items associated with content presented to a user can be determined, as well as the user's response to items with those features. This data is used to determine the probability of the user viewing and/or otherwise engaging an item having specific values for at least some of those features. The probabilities are combined with abandonment scores associated with a feed position of an interface to ensure that content displayed is optimized for engagement. The items can be ranked based on this engagement determination, in order to select which item content to display and the appropriate arrangement of that content.