公开(公告)号：US10891676B1

公开(公告)日：2021-01-12

申请号：US16031885

申请日：2018-07-10

Applicant: Amazon Technologies, Inc.

Inventor： Andrey Kan ,  Christos Faloutsos ,  Xin Luna Dong

IPC: G06Q30/00 ,  G06Q30/06

Abstract: An improved user interface in which related items are grouped intuitively, and ultimately results in the number of navigational steps performed by the user to identify desired related items being reduced, is described herein. For example, instead of having a user interface display a single view that includes all related items, a recommendation system groups the related items based on their respective attribute values and produces data that results in a user interface that displays the related items in these groups. The recommendation system generates labels for these groups such that a user can clearly identify what types of related items are included therein. Thus, a user would not have to browse through a single list of related items ordered in an unfamiliar manner. Rather, a user can browse through smaller subsets of related items, and only in those groups that correspond with attribute values of interest to the user.

公开(公告)号：US11500931B1

公开(公告)日：2022-11-15

申请号：US15996224

申请日：2018-06-01

Applicant: Amazon Technologies, Inc.

Inventor： Panagiotis Parchas ,  Christos Faloutsos ,  Anurag Windlass Gupta ,  Stavros Harizopoulos ,  Michail Petropoulos

IPC: G06F16/90 ,  G06F16/901 ,  G06F16/2455 ,  G06F16/2453

Abstract: Using a graph representation of join history may be performed to distribute database data. Join history may be collected, captured, or tracked which describes the history of join operations between columns of different tables in a database. A graph representation of the join history may be generated. The graph representation may indicate a likelihood of different joins that may be performed between the columns of the tables of a database. An evaluation of the join history may be performed to identify columns for tables in the database to distribute the data of the tables amongst multiple storage locations according to the identified columns.

公开(公告)号：US11276023B1

公开(公告)日：2022-03-15

申请号：US16563447

申请日：2019-09-06

Applicant: Amazon Technologies, Inc.

Inventor： Matthew Butler ,  Christos Faloutsos ,  Mina Loghavi ,  Yi Fan

IPC: G06Q10/00 ,  G06Q10/06 ,  G06N20/00 ,  G06Q20/40

Abstract: Devices and techniques are generally described for fraud detection. A machine learning model is used to determine a first fraud risk score for a first transaction. The machine learning model includes a first set of weights. A first covariance matrix is determined for the machine learning model based at least in part on the first fraud risk score. A second set of weights for the machine learning model is determined. The second set of weights is determined based on the first set of weights and the first covariance matrix. In various examples, the machine learning model with the second set of weights is used to determine a second fraud risk score for a second transaction. A fraud decision surface is determined and the second fraud risk score is compared to the fraud decision surface. Data indicating that the second transaction is fraudulent is sent to a computing device.

公开(公告)号：US11868347B1

公开(公告)日：2024-01-09

申请号：US16698843

申请日：2019-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Yannis Papakonstantinou ,  Balakrishnan Narayanaswamy ,  Christos Faloutsos ,  Vuk Ercegovac

IPC: G06F16/2453 ,  G06F16/2455 ,  G06F16/16 ,  G06F16/23 ,  G06F16/22

CPC classification number: G06F16/24534 ,  G06F16/162 ,  G06F16/2282 ,  G06F16/2393 ,  G06F16/2455

Abstract: Queries that reference materialized views may be rewritten to compensate for stale materialized views. A query may be received that references a materialized view. A determination may be made as to whether the materialized view is stale. For a stale materialized view, the query may be rewritten to generate a query plan that obtains changes made to base tables for the materialized view not included in the stale materialized view and considers the change(s) when generating a result for the query from the materialized view. The rewritten query may then be performed to provide a result as if the materialized view were up-to-date.