Adaptive marketing using insight driven customer interaction

• US 7,996,253 B2
• Filed: 03/05/2010
• Issued: 08/09/2011
• Est. Priority Date: 11/22/2002
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Reed, Kenneth L., Ansusinha, Theodore, Hariharan, Hari S.
• Primary Examiner(s): Choi; Peter
• Application Number:
  US12/718,096
• Publication Number:
  US 20100211456A1
• Time in Patent Office: 522 Days
• Field of Search: 705/7.33
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
• 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
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0254 based on statistics

Abstract

A system and method for adaptive marketing using insight driven customer interaction. The invention uses a closed-loop process for developing insight that may be used to refine further customer interactions. Results of a first customer interaction such as a marketing campaign are stored in a database. The results may be used to retrain predictive models and gain new insights regarding how customers are responding to marketing campaigns. The insights may be used to refine the offers delivered to customers or to extend additional offers in an effort to increase the likelihood that customers will redeem the offers. After each marketing campaign, the results are stored in the database. New and/or modified offers are created based on insights provided by the results of past campaigns. This process may be repeated such that subsequent campaigns are based on insights generated by the predictive models. The insight enables businesses to better target customers with better offers. These offers can be delivered through ensuing marketing campaigns or, through any form of interaction that the business has with the targeted customers.

Claims

1. A method for performing marketing activities, comprising:

providing a system comprising a memory to store instructions, a processor having a plurality of software modules, and a database embodied on non-transitory computer-readable medium to store customer data for a plurality of customers,

wherein the software modules access the instructions stored in the memory and the customer data stored in the database, and

wherein the plurality of software modules comprise a customer data extracting software module and a marketing campaign defining module; and

executing the instructions by the processor to perform the steps of;

extracting the customer data from the database by the customer data extracting software module;

defining a targeted marketing campaign by the marketing campaign defining module, the targeted marketing campaign comprising a selected targeted marketing offer, a selected targeted interaction channel, and a targeted set of customers most likely to accept the targeted marketing offer via the targeted interaction channel, wherein the targeted set of customers is determined by;

segmenting a sample set of the customers into a plurality of customer segments;

describing each of the plurality of customer segments with lift values indicating a likelihood of positive response by a selected customer segment to a selected marketing offer via the targeted interaction channel;

selecting, based on the lift values, a prospect set from the customer segments for potential inclusion in a selected marketing campaign;

assessing with a predictive model a likelihood of acceptance of each customer in the selected prospect set of the selected marketing offer via the targeted interaction channel;

scoring each customer in the selected prospect set with a customer score indicating the likelihood of acceptance;

selecting the targeted set of customers based on the scoring; and

executing the targeted marketing campaign by offering the targeted marketing offer to the targeted set of the customers via the targeted interaction channel;

gathering campaign results data from the targeted marketing campaign by a campaign tracking module, the campaign results data including a count of customers accepting the targeted marketing offer via the targeted interaction channel, and a length of time between making of the targeted marketing offer and the accepting of the targeted marketing offer;

training the predictive model with the campaign results data, wherein the training is based on how the customers respond to various types of the marketing offers and to various types of the interaction channels used in the targeted marketing campaign; and

updating the customer data stored in the database based on the campaign results data.

2. The method of claim 1, further comprising, in a closed-loop process, obtaining insight from campaign results data from the targeted marketing campaign, wherein the insight is used to refine and simplify subsequent customer data extraction and customer selection.

3. The method of claim 1, further comprising:

obtaining insight from the campaign results data with an insight module by comparing the results of the predictive model to the campaign results data; and

developing an additional targeted marketing campaign with the insight to deliver an additional targeted marketing offer to an additional targeted set of customers via an additional targeted interaction channel.

4. The method of claim 1, further comprising creating the predictive model.

5. The method of claim 1, further comprising determining a segment score for a sampled customer in the sample set and associating the sampled customer with one of the customer segments based on the segment score.

6. The method of claim 1, wherein segmenting the sample set comprises overlaying value segments and behavior segments.

7. A system, comprising:

a processor; and

a memory storing instructions operable with the processor for performing marketing activities, the instructions structured throughout a plurality of modules, said modules comprising;

a customer data extracting module configured to extract customer data from a database;

a marketing campaign defining module configured to define a targeted marketing campaign comprising a selected targeted marketing offer, a selected targeted interaction channel, and a targeted set of customers most likely to respond to the targeted marketing offer via the targeted interaction channel wherein the targeted set of customers is determined by;

a segmenting module configured to segment a sample set of the customers into a plurality of customer segments;

a segment description module configured to describe each of the plurality of customer segments with lift values indicating a likelihood of positive response by a selected customer segment to a selected marketing offer via the targeted interaction channel;

a prospect set selecting module configured to select, based on the lift values, a prospect set from the plurality of customer segments for potential inclusion in a selected marketing campaign;

a predictive model module configured to assess a likelihood of acceptance of each customer in the selected prospect set of the selected marketing offer via the targeted interaction channel; and

a prospect set scoring module configured to score each customer in the selected prospect set with a customer score indicating the likelihood of acceptance; and

a customer selection module configured to select the targeted set of customers based on the customer score; and

an execution module configured to execute the targeted marketing campaign by offering the targeted marketing offer to the targeted set of the customers via the targeted interaction channel;

a campaign tracking module configured to gather campaign results data from the targeted marketing campaign, the campaign results data including a count of customers accepting the targeted marketing offer via the targeted interaction channel, and a length of time between making of the targeted marketing offer and the accepting of the targeted marketing offer;

a training module for training the predictive model with the campaign results data, wherein the training is based on how the customers respond to various types of the marketing offers and to various types of the interaction channels used in the targeted marketing campaign; and

an updating module for updating the customer data stored in the database based on the campaign results data.

8. The system of claim 7, further comprising an analysis module configured to analyze insight obtained from campaign results data from the targeted marketing campaign to refine and simplify subsequent customer data extraction and customer selection.

9. The system of claim 7, further comprising:

an insight module configured to obtain insight from the campaign results data by comparing the results of the predictive mode to the campaign results data; and

an additional targeted marketing campaign development module configured to develop an additional targeted marketing campaign to deliver an additional targeted marketing offer to an additional targeted set of customers via an additional targeted interaction channel.

10. The system of claim 7, further comprising a predictive model creating module configured to create the predictive model.

11. The system of claim 7, wherein the segmenting module is configured to use variables that indicate a customer'"'"'s behavior.

12. The system of claim 7, wherein the segmenting module is configured to use a customer lifetime value as a driving variable.

13. The system of claim 7, further comprising an overlaying module configured to overlay value segments and behavior segments.

14. A computer program embodied on a non-transitory computer readable medium for performing marketing activities, wherein the computer program instructs a processor to perform a method comprising:

accessing instructions for a plurality of software modules stored in a memory, wherein the plurality of software modules comprise a customer data extracting software module and a marketing campaign defining module;

accessing customer data stored in a database for a plurality of customers; and

executing, by the processor, the instructions to perform the steps of;

extracting the customer data from the database by the customer data extracting software module;

defining a targeted marketing campaign by the marketing campaign defining module, the targeted marketing campaign comprising a selected targeted marketing offer, a selected targeted interaction channel, and a targeted set of customers most likely to accept the targeted marketing offer via the targeted interaction channel, wherein the targeted set of customers is determined by;

segmenting a sample set of the customers into a plurality of customer segments;

describing each of the plurality of customer segments with lift values indicating a likelihood of positive response by a selected customer segment to a selected marketing offer via the targeted interaction channel;

selecting, based on the lift values, a prospect set from the customer segments for potential inclusion in a selected marketing campaign;

assessing with a predictive model a likelihood of acceptance of each customer in the selected prospect set of the selected marketing offer via the targeted interaction channel;

scoring each customer in the selected prospect set with a customer score indicating the likelihood of acceptance;

selecting the targeted set of customers based on the scoring; and

executing the targeted marketing campaign by offering the targeted marketing offer to the targeted set of the customers via the targeted interaction channel;

gathering campaign results data from the targeted marketing campaign by a campaign tracking module, the campaign results data including a count of customers accepting the targeted marketing offer via the targeted interaction channel, and a length of time between making of the targeted marketing offer and the accepting of the targeted marketing offer; and

training the predictive model with the campaign results data, wherein the training is based on how the customers respond to various types of the marketing offers and to various types of the interaction channels used in the targeted marketing campaign; and

updating the customer data stored in the database based on the campaign results data.

15. The computer program of claim 14, wherein the method further comprises executing the instructions to obtain, in a closed-loop process, insight from campaign results data from the targeted marketing campaign, wherein the insight is used to refine and simplify subsequent customer data extraction and customer selection.

16. The computer program of claim 14, wherein the method further comprises executing the instructions to perform:

obtaining insight from the campaign results data with an insight module by comparing the results of the predictive model to the campaign results data; and

developing an additional targeted marketing campaign with the insight to deliver an additional targeted marketing offer to an additional targeted set of customers via an additional targeted interaction channel.

17. The computer program of claim 14, wherein extracting the customer data comprises selecting data from a database view that comprises at least a portion of data from the database and a transform that has been developed from the data from the database.

18. The computer program of claim 17, wherein a database object includes the database view.