FALSE POSITIVE REDUCTION IN ABNORMALITY DETECTION SYSTEM MODELS
First Claim
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.
1 Assignment
0 Petitions
Accused Products
Abstract
The subject matter disclosed herein provides methods, apparatus, systems, techniques, and articles for false positive reduction in abnormality detection models. A date and time of a first transaction by a transaction entity and associated with a transaction characteristic can be stored. Data representing subsequent transactions associated with the transaction characteristic can be stored. A history marker profile specific to the transaction characteristic and transaction entity can be generated and can include the transaction characteristic, the date and time of the first transaction, and maximum and mean abnormality scores. A date and time of a current transaction can be determined. A current abnormality score for the current transaction can be received. A tenure of the observed transaction characteristic can be computed. The current abnormality score can be recalibrated from the transaction entity abnormality detection system according to the maximum, mean, and current abnormality scores and a length of the tenure.
-
Citations
21 Claims
-
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 Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system comprising:
-
at least one processor; and at least one memory, wherein the at least one processor and the at least one memory are configured to perform operations 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 Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory computer-readable medium containing instructions to configure a processor to perform operations 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 Dependent Claims (16, 17, 18, 19, 20, 21)
-
Specification