×

FALSE POSITIVE REDUCTION IN ABNORMALITY DETECTION SYSTEM MODELS

  • US 20200134629A1
  • Filed: 12/23/2019
  • Published: 04/30/2020
  • Est. Priority Date: 05/29/2015
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising:

  • receiving, from a transaction entity abnormality detection system, at least one abnormality score representing a likelihood of abnormality for a first transaction and one or more subsequent transactions by a transaction entity associated with at least one merchant characteristic, the abnormality score being recursively updated based on the first transaction and the one or more subsequent transactions;

    determining, by at least one data processor, a date and time of a current transaction received via a network from the transaction entity, the current transaction associated with the at least one transaction characteristic;

    receiving, by the at least one data processor from the transaction entity abnormality detection system, a current abnormality score representing a likelihood of abnormality for the current transaction;

    computing, by the at least one data processor, a tenure of the at least one transaction characteristic by subtracting the date and time of the first transaction by the transaction entity with the at least one transaction characteristic from the date and time of the current transaction by the transaction entity with the at least one transaction characteristic; and

    recalibrating, by the at least one data processor, the current abnormality score from the transaction entity abnormality detection system according to the at least one abnormality score, the current abnormality score, and a length of the tenure.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×