SYSTEMS, APPARATUSES, AND METHODS FOR INTELLIGENT NETWORK COMMUNICATION AND ENGAGEMENT

    公开(公告)号:US20190068728A1

    公开(公告)日:2019-02-28

    申请号:US16113712

    申请日:2018-08-27

    Abstract: Systems and methods directed to intelligent network communication and engagement during interaction with a consumer device. The progress of the consumer/consumer device can be tracked during interaction to make a decision to intervene based on one or more factors. The intervention may include invoking an appropriate, personalized request to the consumer for support. A consumer device can be employed to shop for a product via a mobile application provided by a retailer. For example, if the client has placed an item in a shopping cart, but does not completed the transaction, the context service can track events associated with the interaction and using an analysis service, and determine an appropriate time and/or manner to communicatively engage the user. As such, the context service can mimic a brick and mortar sales experience where sales associates determine the appropriate time to interact with a client who appears confused.

    MULTIVARIATE RISK ASSESSMENT VIA POISSON SHELVES

    公开(公告)号:US20220405660A1

    公开(公告)日:2022-12-22

    申请号:US17745400

    申请日:2022-05-16

    Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

    Risk assessment using Poisson Shelves

    公开(公告)号:US11334832B2

    公开(公告)日:2022-05-17

    申请号:US16589511

    申请日:2019-10-01

    Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

    MULTIVARIATE RISK ASSESSMENT VIA POISSON SHELVES

    公开(公告)号:US20220351099A1

    公开(公告)日:2022-11-03

    申请号:US17745422

    申请日:2022-05-16

    Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

    MULTIVARIATE RISK ASSESSMENT VIA POISSON SHELVES

    公开(公告)号:US20230004891A1

    公开(公告)日:2023-01-05

    申请号:US17939632

    申请日:2022-09-07

    Abstract: Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

Patent Agency Ranking