METHOD AND APPARATUS FOR PREDICTING CUSTOMER CHURN

• US 20090292583A1
• Filed: 05/07/2008
• Published: 11/26/2009
• Est. Priority Date: 05/07/2008
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Lam, Hila, Lubowich, Yuval, Eilam, Barak
• Granted Patent: US 8,615,419 B2
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0224 based on user history
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method and apparatus for predicting customer churn from an organization. The method and apparatus determine an interaction churn score based on analyzing an interaction between the customer and the organization and related data. Optionally, the method and apparatus determine also a transactional churn score based on additional data related to the customer or the organization, and a combined churn score based on the interaction churn score and the transactional churn score. The interaction churn score is determined by assessing a categorization score for the interaction in association with one or more categories, and combining the categorization scores. Of further use is a retention offer mechanism for making a retention offer to the customer.

Claims

1. A method for providing a prediction for customer churn in an organization with which the customer has an interaction, the method comprising determining an interaction churn score for the interaction.

2. The method of claim 1 further comprising the steps of:

determining or receiving a transactional churn score based on additional data related to the customer or to the organization; and

combining the interaction churn score and transactional churn score into a combined churn score.

3. The method of claim 1 further comprising a step of extracting data from the interaction for determining the interaction churn score.

4. The method of claim 3 wherein the data includes at least one item selected from the group consisting of:

speech to text data, word spotting data, emotional level detection data, call flow analysis data, Computer Telephony Integration data, Customer Relationship Management data, or Business Intelligence data.

5. The method of claim 1 further comprising a step of making a retention offer to the customer.

6. The method of claim 1 wherein determining the interaction churn score comprises the steps of:

categorizing the interaction into at least one category, by determining at least one category-interaction indication associating the interaction with the at least one category; and

combining the at least one category-interaction indication into the interaction churn score.

7. The method of claim 6 wherein combining the at least one category-interaction indication is based on at least one item selected from the group consisting of:

a maximal indication between the interaction and the at least one category, and a number of churning categories the interaction is associated with out of a total number of churning categories.

8. The method of claim 6 further comprising a step of defining the at least one category.

9. The method of claim 1 further comprising a step of performing quality monitoring for an agent associated with the interaction.

10. The method of claim 1 further comprising a step of performing at least one action, or for generating or handling at least one alert based on the combined churn score.

11. The method of claim 10 wherein the action relates to opening a ticket in a business intelligence system or tool or in a customer relationship management system or tool.

12. An apparatus for providing a prediction for customer churn in an organization with which the customer has an interaction, the apparatus comprising an interaction churn score determination component for determining an interaction churn score related to the interaction.

13. The apparatus of claim 12 further comprising:

a transactional churn score determination component for determining a transaction churn score for the customer, based on additional data related to the customer or to the organization; and

a combined churn score determination component for combining the interaction churn score and the transaction churn score into a combined churn score.

14. The apparatus of claim 12 further comprising an extraction engine for extracting information from the interaction.

15. The apparatus of claim 14 wherein the extraction engine is at least one item selected from the group consisting of:

a speech to text engine, a word spotting engine, a phonetic search engine, an acoustic extraction engine, and an external feature extraction engine.

16. The apparatus of claim 15 wherein the external feature extraction engine extracts information from at least one item selected from the group consisting of:

a Computer Telephony Integration system, a Customer Relationship Management system, and a Business Intelligence system.

17. The apparatus of claim 12 further comprising a retention offer engine for making a retention offer to the customer.

18. The apparatus of claim 12 further comprising a category score determination component for determining at least one category-interaction indication associating the interaction with at least one category.

19. The apparatus of claim 18 further comprising a category definition component for defining the at least one category.

20. The apparatus of claim 12 further comprising a reactive component for taking at least one action, or for generating or handling at least one alert based on the combined churn score.

21. The apparatus of claim 20 wherein the action relates to opening a ticket in a business intelligence system or tool, or in a customer relationship management system or tool.

22. The apparatus of claim 12 further comprising a quality management component for monitoring a quality parameter of an agent associated with the interaction.

23. An apparatus for providing a prediction for customer churn in an organization with which the customer has an interaction, the apparatus comprising:

an extraction engine for extracting information from the interaction;

a category score determination component for determining at least one category-interaction indication associating the interaction with at least one category;

an interaction churn score determination component for determining an interaction churn score related to the interaction;

a transactional churn score determination component for determining a transaction churn score for the customer, based on additional data related to the customer or to the organization;

a combined churn score determination component for combining the interaction churn score and the transaction churn score into a combined churn score;

a retention offer engine for making a retention offer to the customer; and

a capturing or logging component for capturing the interaction.

24. The apparatus of claim 23 further comprising a storage device for storing the at least one category and parameters thereof.

25. The apparatus of claim 23 further comprising a quality management component for monitoring a quality parameter of an agent associated with the interaction.

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

determining an interaction churn score for an interaction between a customer and an organization;

determining a transactional churn score based on additional data related to the customer or to the organization; and

combining the interaction churn score and transactional churn score into a combined churn score.