Churn prediction and management system

• US 8,712,828 B2
• Filed: 02/03/2006
• Issued: 04/29/2014
• Est. Priority Date: 12/30/2005
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Maga, Matteo, Canale, Paolo, Bohe, Astrid
• Primary Examiner(s): Nguyen, Nga B.
• Application Number:
  US11/347,141
• Publication Number:
  US 20070156673A1
• Time in Patent Office: 3,007 Days
• Field of Search: 705/7, 705/10, 705/14
• US Class Current: 705/10
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

A system and method for managing churn among the customers of a business is provided. The system and method provide for an analysis of the causes of customer churn and identifies customers who are most likely to churn in the future. Identifying likely churners allows appropriate steps to be taken to prevent customers who are likely to churn from actually churning. The system included a dedicated data mart, a population architecture, a data manipulation module, a data mining tool and an end user access module for accessing results and preparing preconfigured reports. The method includes adopting an appropriate definition of churn, analyzing historical customer to identify significant trends and variables, preparing data for data mining, training a prediction model, verifying the results, deploying the model, defining retention targets, and identifying the most responsive targets.

Claims

1. A system for managing churn among customers of a business having a statistically large customer base, the system comprising:

a memory device configured to store a data mart;

a processor in communication with the memory device;

a population architecture executable by the processor to receive customer data from one or more data sources stored in the data mart, the customer data defining a plurality of customer attributes for each customer in the customer base;

a data manipulation module executable by the processor to;

calculate derived variable values based on the customer data, wherein each of the derived variable values is indicative of at least one customer characteristic;

select a subset of the derived variable values in response to a preselected data mining function; and

generate at least one analytical record containing the subset of the derived variable values, wherein the at least one analytical record is associated with a plurality of customers;

a data mining tool executable by the processor to perform the preselected data mining function, the preselected data mining function configured to;

analyze the at least one analytical record;

return results identifying clusters of customers sharing common customer attributes in response to the analysis of the at least one analytical record; and

calculate, based on the at least one analytical record, individual customers'"'"' propensities to churn during a predefined period in the future, the data manipulation module storing the results in the data mart; and

an end user access module executable by the processor to;

access the results returned from the data mining tool; and

present the results to a user.

2. The system for managing churn of claim 1 wherein the data mining tool comprises an SAS Enterprise Miner.

3. The system for managing churn of claim 1 wherein the data mining tool comprises a KXEN data mining tool.

4. The system for managing churn of claim 1 wherein the subset of derived variable values included in the analytical record are selected to provide customer behavioral data to the data mining tool, and wherein the data mining tool is further executable by the processor to identify significant clusters of customers based on common behavioral characteristics.

5. The system for managing churn of claim 1 wherein the subset of derived variable values included in the analytical record are selected to provide customer value data to the data mining tool, and wherein the data mining tool is further executable by the processor to identify significant clusters of customers based on common value characteristics.

6. The system for managing churn of claim 1 wherein the subset of derived variable values included in the analytical record are selected to provide customer data to the data mining tool, and wherein the data mining tool is further executable by the processor to calculate individual customers'"'"' propensities to churn based on the subset of derived variable values.

7. The system for managing churn of claim 1 wherein the end user access module is further executable by the processor to generate one or more reports configured to analyze churn based on customer data stored in the data mart.

8. The system for managing churn of claim 7 wherein a report compares active customers to churned customers.

9. The system of claim 7 wherein the end user access module is further executable by the processor to:

calculate a churn rate from historical data; and

generate a report that illustrates the churn rated versus classes of customers defined according to customer distribution relative to a selected customer attribute.

10. The system of claim 7 wherein the end user access module is further executable by the processor to:

calculate a churn rate; and

generate a report that illustrates the churn rate for a cluster of customers.

11. The system of claim 7 wherein the end user access module is further executable by the processor to:

calculate a churn rate; and

generates a report that illustrates the churn rate versus a first behavioral cluster variable, and a second value cluster variable.