Patents by Inventor Jon E Elvin

Jon E Elvin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Risk clustering and segmentation
    Patent number: 12293377
    Abstract: Monitoring transaction activity for system requests for a set of entities authorized to request services of a system is described. Entities with high feature values for respective features of the set of activity based features are identified to produce a set of outlier entities. The outlier entities are filtered from the set of entities. A set of clusters are created from the filtered set of entities based on the set of activity based features so that each entity in the filtered set of entities is assigned to a cluster. Values for the set of activity based features are established for each cluster. A risk is assigned for each cluster based on the values of one or more of the set of activity based features. Each of the filtered set of entities are monitored based on the risk assigned to the respective clusters to which the respective entities belong.
    Type: Grant
    Filed: March 31, 2021
    Date of Patent: May 6, 2025
    Assignee: International Business Machines Corporation
    Inventors: Christopher Sidler, Raymond Strecker, Michael A Dawson, Sankar Virdhagriswaran, Jon E Elvin
  • RISK CLUSTERING AND SEGMENTATION
    Publication number: 20220318819
    Abstract: Monitoring transaction activity for system requests for a set of entities authorized to request services of a system is described. Entities with high feature values for respective features of the set of activity based features are identified to produce a set of outlier entities. The outlier entities are filtered from the set of entities. A set of clusters are created from the filtered set of entities based on the set of activity based features so that each entity in the filtered set of entities is assigned to a cluster. Values for the set of activity based features are established for each cluster. A risk is assigned for each cluster based on the values of one or more of the set of activity based features. Each of the filtered set of entities are monitored based on the risk assigned to the respective clusters to which the respective entities belong.
    Type: Application
    Filed: March 31, 2021
    Publication date: October 6, 2022
    Inventors: Christopher Sidler, Raymond Strecker, Michael A Dawson, Sankar Virdhagriswaran, Jon E Elvin