SYSTEMS AND METHODS FOR MERGING NETWORKS OF HETEROGENEOUS DATA
    51.
    发明申请
    SYSTEMS AND METHODS FOR MERGING NETWORKS OF HETEROGENEOUS DATA 审中-公开
    用于整合异构数据网络的系统和方法

    公开(公告)号:US20170017806A1

    公开(公告)日:2017-01-19

    申请号:US15209970

    申请日:2016-07-14

    CPC classification number: G06Q30/02 G06Q30/0255 G06Q30/0631

    Abstract: A method and system for merging heterogeneous data types are provided. The method includes receiving a first corpus of first data, the first data includes an indicator of an interaction between a first element of the first corpus of first data and a second element of the first corpus of first data, receiving a second corpus of second data, the second data includes an indication of an interaction between a third element of the second corpus of second data and a fourth element of the second corpus of data, and generating a third matrix using correlations of the first and second elements with correlations of the third and fourth elements.

    Abstract translation: 提供了一种用于合并异构数据类型的方法和系统。 该方法包括接收第一数据的第一语料库,第一数据包括第一数据的第一语料库的第一元素与第一数据的第一语料库的第二元素之间的交互的指示符,接收第二数据的第二语料库 第二数据包括第二数据的第二语料库的第三元素与第二数据库的第四元素之间的交互的指示,以及使用第一和第二元素的相关性与第三数据的相关性来生成第三矩阵 和第四要素。

    Systems and methods for improved detection of network fraud events

    公开(公告)号:US12229781B2

    公开(公告)日:2025-02-18

    申请号:US17510203

    申请日:2021-10-25

    Abstract: A method and system for detecting fraudulent network events in a payment card network are provided. A plurality of scored payment card transaction authorization requests is received, originating from a plurality of merchants, and data structures for each of a plurality of merchant groups are generated. Each data structure sorts the scored authorization requests into fraud score range stripes. The data structures are parsed over a plurality of time periods, and at least one cumulative metric is calculated for each merchant group for each of the time periods in each fraud score range stripe. A plurality of ratio striping values is determined for each merchant group, and a set of feature inputs is generated using the ratio striping values. A second fraud detection model is applied to the scored authorization requests. Parameters of the second fraud detection model are configured to change based on the generated set of feature inputs.

    SYSTEMS AND METHODS FOR ADVANCED USER AUTHENTICATION IN ACCESSING A COMPUTER NETWORK

    公开(公告)号:US20240273536A1

    公开(公告)日:2024-08-15

    申请号:US18167694

    申请日:2023-02-10

    CPC classification number: G06Q20/4016 G06Q20/4014 G06Q20/405

    Abstract: An authentication platform for authenticating an online user is provided. The authentication platform includes a memory device including an authentication profile and at least one processor coupled to the memory device. The at least one processor is programmed to collect a plurality of authentication data from a plurality of transactions initiated by users attempting to perform a transaction over a computer network, analyze the plurality of authentication data to detect a plurality of insights representing relationships between data elements of different authentication requests of the plurality of authentication requests, wherein the insights represent a likelihood of fraud or potential approval with the corresponding authentication requests, determine a plurality of rules from the plurality of insights, filter the plurality of rules based on one or more thresholds, and provide the filtered plurality of rules to analyze a plurality of subsequent real-time transactions for detecting legitimate authentication requests.

    SYSTEMS AND METHODS FOR IDENTIFYING FULL ACCOUNT NUMBERS FROM PARTIAL ACCOUNT NUMBERS

    公开(公告)号:US20240242274A1

    公开(公告)日:2024-07-18

    申请号:US18623893

    申请日:2024-04-01

    CPC classification number: G06Q40/02 G06F16/9017 G06F17/18

    Abstract: A system for identifying complete account identifiers from partial account identifiers is provided. The system includes an account identification computing device including at least one processor and a memory device in communication with the at least one processor. The processor is configured to receive transaction data including unique merchant identifiers, build a merchant table using the transaction data, and receive a list including partial account identifiers. The processor is further configured to determine, for each unique merchant identifier, a number of candidate account identifiers and calculate at least one metric based on the number of candidate account identifiers. The processor is further configured to identify a source unique merchant identifier and match at least one candidate account identifier to a complete account identifier by matching one of the partial account identifiers to the at least one candidate account identifier.

    SYSTEMS AND METHODS FOR MERGING NETWORKS OF HETEROGENEOUS DATA

    公开(公告)号:US20240112204A1

    公开(公告)日:2024-04-04

    申请号:US18486847

    申请日:2023-10-13

    CPC classification number: G06Q30/02 G06Q30/0255 G06Q30/0631

    Abstract: A method and system for merging heterogeneous data types are provided. The method includes receiving a first corpus of first data, the first data includes an indicator of an interaction between a first element of the first corpus of first data and a second element of the first corpus of first data, receiving a second corpus of second data, the second data includes an indication of an interaction between a third element of the second corpus of second data and a fourth element of the second corpus of data, and generating a third matrix using correlations of the first and second elements with correlations of the third and fourth elements.

    Systems and methods for identifying full account numbers from partial account numbers

    公开(公告)号:US11948189B2

    公开(公告)日:2024-04-02

    申请号:US17138437

    申请日:2020-12-30

    CPC classification number: G06Q40/02 G06F16/9017 G06F17/18

    Abstract: A system for identifying complete account identifiers from partial account identifiers is provided. The system includes an account identification computing device including at least one processor and a memory device in communication with the at least one processor. The processor is configured to receive transaction data including unique merchant identifiers, build a merchant table using the transaction data, and receive a list including partial account identifiers. The processor is further configured to determine, for each unique merchant identifier, a number of candidate account identifiers and calculate at least one metric based on the number of candidate account identifiers. The processor is further configured to identify a source unique merchant identifier and match at least one candidate account identifier to a complete account identifier by matching one of the partial account identifiers to the at least one candidate account identifier.

    Entity identification based on a record pattern

    公开(公告)号:US11562361B2

    公开(公告)日:2023-01-24

    申请号:US15847924

    申请日:2017-12-20

    Abstract: The methods described herein are configured to obtain a first record pattern associated with the unidentified entity and select a second record pattern associated with an entity identifier of a known entity. Based on the first record pattern matching the second record pattern, the entity identifier of the known entity is associated to the unidentified entity to indicate that the unidentified entity and the known entity are the same. Determining the entity identifier of the unidentified entity enables the linking of separate identifier systems of data structures to facilitate communication and/or interaction between the data structures.

    SYSTEMS AND METHODS FOR IDENTIFYING FULL ACCOUNT NUMBERS FROM PARTIAL ACCOUNT NUMBERS

    公开(公告)号:US20220207601A1

    公开(公告)日:2022-06-30

    申请号:US17138437

    申请日:2020-12-30

    Abstract: A system for identifying complete account identifiers from partial account identifiers is provided. The system includes an account identification computing device including at least one processor and a memory device in communication with the at least one processor. The processor is configured to receive transaction data including unique merchant identifiers, build a merchant table using the transaction data, and receive a list including partial account identifiers. The processor is further configured to determine, for each unique merchant identifier, a number of candidate account identifiers and calculate at least one metric based on the number of candidate account identifiers. The processor is further configured to identify a source unique merchant identifier and match at least one candidate account identifier to a complete account identifier by matching one of the partial account identifiers to the at least one candidate account identifier.

Patent Agency Ranking