APPARATUS AND METHOD FOR FRAUD PREVENTION

• US 20100228656A1
• Filed: 03/09/2009
• Published: 09/09/2010
• Est. Priority Date: 03/09/2009
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: WASSERBLAT, Moshe, Lubowich, Yuval
• Granted Patent: US 8,145,562 B2
• Time in Patent Office: Days
• US Class Current: 705/35
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof

Abstract

The disclosed method and apparatus combine interactions and transactions in order to detect fraud acts or fraud attempts. In one embodiment, one or more interactions is correlated with one or more transactions, the interactions is and transactions features are combined, and features are extracted from the combined structure. The features are compared against one or more profiles, and a combined risk score is determined for the interactions or transactions. If the risk score exceeds a predetermined threshold, a preventive/corrective action can be taken.

In another embodiment, behavioral characteristics extracted from one or more interactions associated with a transaction, with a risk score obtained by analyzing the transaction. The behavioral characteristic are used to enhance suspicion level related to a transaction being fraudulent, and to enable the taking of measures related to the transaction or to the person handling the transaction. The combination thus enables better assessment whether a particular interaction or transaction is fraudulent, and therefore provides for better detection or prevention of such activities. In addition, making the fraud assessment more reliable enables more efficient resource allocation of personnel for monitoring the transactions and interactions, better usage of communication time by avoiding lengthy identification where not required, and generally higher efficiency.

Claims

1. A method for detecting a fraud act or a fraud attempt represented in an at least one interaction in a call center associated with an organization, the method comprising the steps of:

receiving the at least one interaction captured by a capturing or logging device;

correlating the at least one interaction with an at least one transaction;

receiving the at least one transaction;

combining the at least one interaction and the at least one transaction into a combined structure;

extracting at least two features from the combined structure by at least two extraction components;

scoring the at least two features against a user profile to obtain a combined score; and

taking a safety measure in accordance with said combined score.

2. The method of claim 1 further comprising the step of generating the user profile.

3. The method of claim 2 wherein the user profile comprises a behavioral characteristic and a transactional characteristic.

4. The method of claim 1 wherein at least one of the at least two features is selected from the group consisting of:

a vocal feature;

a behavioral feature; and

a textual feature; and

wherein at least one of the at least two features is a transactional feature.

5. The method of claim 1 wherein the interaction is a vocal interaction or a textual interaction.

6. The method of claim 1 further comprising a speech to text step for extracting text from the at least one interaction.

7. The method of claim 1 further comprising a training step for training at least one of the at least two extraction component.

8. An apparatus for detecting a fraud act or a fraud attempt represented in at least one interaction in a call center associated with an organization, the apparatus comprising:

a capturing or logging device for capturing at least one interaction associated with the transaction and captured in a contact center associated with the organization;

an interaction and transaction correlation component for correlating the at least one interaction with an at least one transaction, thereby creating a combined structure;

at least two extraction components each arranged to extract at least one feature from the combined structure;

a transaction and interaction scoring component for scoring the at least one feature against a user profile to obtain a combined score; and

a profiling component for generating the user profile.

9. The apparatus of claim 8 wherein one of the at least two extraction components is selected from the group consisting of:

an acoustic indicator extraction component;

a stress level extraction engine;

an emotion level extraction engine;

a sentiment level extraction engine;

a talk patter extraction engine;

a gender extraction engine;

a linguistic indicator extraction engine;

a textual indicator extraction component;

a context or language model mismatch extraction engine;

a Natural Language Processing mismatch extraction engine and a voice print matching engine, and wherein one of the at least two extraction components is a transactional extraction component.

10. The apparatus of claim 8 further comprising a speech to text engine for extracting text from at least one vocal interaction.

11. A computer readable storage medium containing a set of instructions for a general purpose computer, the set of instructions comprising:

receiving at least one interaction captured by a capturing or logging;

correlating the at least one interaction with an at least one transaction;

receiving the at least one transaction;

combining the at least one interaction and the at least one transaction into a combined structure;

extracting at least two features from the combined structure by at least two extraction components;

scoring the at least two features against a user profile to obtain a combined score; and

taking a safety measure in accordance with said combined score.

12. A method for detecting a fraud act or a fraud attempt represented in at least one interaction in a call center associated with an organization, the method comprising the steps of:

receiving the at least one interaction captured by a capturing or logging device;

extracting at least one feature from the at least one interaction by at least one extraction component;

correlating the interaction with at least one transaction;

receiving the at least one transaction;

scoring the at least one transaction against a profile to obtain a first score;

combining the first score with the at least one feature to obtain a combined score; and

taking a safety measure in accordance with said combined score.

13. The method of claim 12 wherein the profile is selected from the group consisting of:

a user profile, a user group profile, a transaction profile, and a transaction type profile.

14. The method of claim 12 wherein the at least one feature is a vocal feature or a textual feature.

15. The method of claim 12 further comprising a speech to text step for extracting text from at least one vocal interaction.

16. The method of claim 12 further comprising a training step for training the at least one extraction component.

17. An apparatus for analyzing at least one transaction associated with an organization, the apparatus comprising:

a capturing or logging device for capturing at least one interaction associated with the transaction and captured in a contact center associated with the organization;

a transaction and interaction correlation component for associating the at least one interaction with the at least one transaction.

an extraction component arranged to extract at least one feature from the at least one interaction;

a transaction scoring component for associating a first score with the at least one transaction; and

a combined scoring component for combining the at least one feature with the first score to obtain a combined score for the at least one transaction.

18. The apparatus of claim 17 wherein the extraction component is an acoustic indicator extraction component.

19. The apparatus of claim 17 wherein the extraction component is a textual indicator extraction component.

20. The apparatus claim 17 further comprising a speech to text engine for extracting text from at least one vocal interaction.