Using both social media and non-social media information to identify anomalous behavior
AssigneeInternational Business Machines Corporation
InventorsDavid L. Kaminsky, Girish Sundaram
Life of this patent
Estimating the term…
Loading patent…
AssigneeInternational Business Machines Corporation
InventorsDavid L. Kaminsky, Girish Sundaram
Estimating the term…
A method, system and computer program product for identifying anomalous behavior (e.g., suspicious transactions). Information from at least one social media source (e.g., a posting) and from at least one non-social media source (e.g., a booking) are monitored. A transaction (e.g., credit card transaction) involving a user is identified. The monitored information is then analyzed to identify one or more characteristics (e.g., location of the user) of the user. A rating of invalidity of the transaction is generated based on the one or more characteristics, where the rating of invalidity refers to the likelihood that the transaction is likely to be anomaly, such as a suspicious transaction. If the rating exceeds a threshold, then an anomaly may be said to have occurred. By identifying anomalous behavior using both social media and non-social media sources, anomalous activities that truly occurred will be more accurately detected.
A method for identifying anomalous behavior, the method comprising:
A computer program product embodied in a computer readable storage medium for identifying anomalous behavior, the computer program product comprising the programming instructions for:
A system, comprising:
Dependencies are inferred from the claim text.