Apparatus and method for predicting customer behavior

• US 9,536,248 B2
• Filed: 05/08/2015
• Issued: 01/03/2017
• Est. Priority Date: 02/22/2006
• Status: Active Grant

• Current Assignee: [24]7.ai, Inc.
• Original Assignee: 24/7 Customer Incorporated
• Inventors: Kannan, Pallipuram V., Jain, Mohit, Vijayaraghavan, Ravi
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US14/707,904
• Publication Number:
  US 20150242860A1
• Time in Patent Office: 606 Days
• Field of Search: 705 711- 742, 707600-606, 703/22, 379/265.06
• US Class Current: 1/1
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/016 After-sales
• 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 predictive model generator that enhances customer experience, reduces the cost of servicing a customer, and prevents customer attrition by predicting the appropriate interaction channel through analysis of different types of data and filtering of irrelevant data. The model includes a customer interaction data engine for transforming data into a proper format for storage, data warehouse for receiving data from a variety of sources, and a predictive engine for analyzing the data and building models.

Claims

1. A computer-implemented method for assigning an interaction channel to a customer comprising:

receiving problem data relating to a customer interaction arising from a purchase of a product or service;

receiving product data relating to the product or service purchased by a customer during the customer interaction;

receiving information about the customer that purchased the product or service;

transforming the problem data, product data, and the information about the customer into data;

determining, using a computing platform comprising at least one processor, contributing variables using the data, wherein the determining comprises computing contributing variables according to whether the variable is for a numerical or categorical prediction;

building a plurality of predictive models using the contributing variables, wherein any of the plurality of predictive models is configured to predict any of;

a probability of a customer to face a particular problem or issue based on an engagement stage of the customer with the company, wherein the engagement stage is product or service specific and measured by time after purchase or is the stage of a life cycle of the customer;

a customer'"'"'s preference of a particular channel based on type of concern and reduction of resolution time through the particular channel; and

a probable impact of a particular problem on a customer'"'"'s loyalty, growth, and profitability score; and

selecting and assigning an interaction channel to the customer from among a plurality of interaction channels based upon any of the plurality of predictive models.

2. The method of claim 1 further comprising testing and validating the plurality of predictive models.

3. The method of claim 1 further comprising receiving a request to generate a predictive model for a particular customer using, among other things, the contributing variables.

4. The method of claim 3 further comprising generating the customer predictive model.

5. The method of claim 1 further comprising receiving information about an agent and transforming that information about the agent into the data.

6. The method of claim 1 further comprising predicting an appropriate interaction channel, using the predictive models, for the customer.

7. The method of claim 6 wherein the predicting of the appropriate interaction channel is based on filtering of irrelevant data from the data.

8. The method of claim 1 further comprising predicting customer attrition based on the prediction models.

9. The method of claim 8 further comprising offering an appropriate interaction channel in order to prevent the customer attrition.

10. The method of claim 8 further comprising handling a service request by a specific agent in order to prevent customer attrition.

11. The method of claim 1 further comprising identifying trends in customer behavior based on the customer interaction.

12. The method of claim 11 wherein the trend is a function of an agent.

13. The method of claim 1 wherein the building is in real time.

14. The method of claim 1 wherein contributing variables for a numerical prediction or a categorical prediction are computed using one or more statistical or predictive algorithms comprising one or more of linear regression, logistic regression, Naï

ve Bayes, neural networks, and support vector machines.

15. A computer system for assigning an interaction channel to a customer comprising:

a memory which stores instructions;

one or more processors coupled to the memory wherein the one or more processors are configured to;

receive problem data relating to a customer interaction arising from a purchase of a product or service;

receive product data relating to the product or service purchased by a customer during the customer interaction;

receive information about the customer that purchased the product or service;

transform the problem data, product data, and the information about the customer into data;

determine contributing variables using the data, wherein the determining comprises computing contributing variables according to whether the variable is for a numerical or categorical prediction;

build a plurality of predictive models using the contributing variables, wherein any of the plurality of predictive models is configured to predict any of;

a probability of a customer to face a particular problem or issue based on an engagement stage of the customer with the company, wherein the engagement stage is product or service specific and measured by time after purchase or is the stage of a life cycle of the customer;

a customer'"'"'s preference of a particular channel based on type of concern and reduction of resolution time through the particular channel; and

a probable impact of a particular problem on a customer'"'"'s loyalty, growth, and profitability score; and

select and assign an interaction channel to the customer from among a plurality of interaction channels based upon any of the plurality of predictive models.

16. A computer program product embodied in a non-transitory computer readable medium for assigning an interaction channel to a customer comprising:

code for receiving problem data relating to a customer interaction arising from a purchase of a product or service;

code for receiving product data relating to the product or service purchased by a customer during the customer interaction;

code for receiving information about the customer that purchased the product or service;

code for transforming the problem data, product data, and the information about the customer into data;

code for determining, using a computing platform comprising at least one processor, contributing variables using the data, wherein the determining comprises computing contributing variables according to whether the variable is for a numerical or categorical prediction;

code for building a plurality of predictive models using the contributing variables, wherein any of the plurality of predictive models is configured to predict any of;

a probability of a customer to face a particular problem or issue based on an engagement stage of the customer with the company, wherein the engagement stage is product or service specific and measured by time after purchase or is the stage of a life cycle of the customer;

a customer'"'"'s preference of a particular channel based on type of concern and reduction of resolution time through the particular channel; and

a probable impact of a particular problem on a customer'"'"'s loyalty, growth, and profitability score; and

code for selecting and assigning an interaction channel to the customer from among a plurality of interaction channels based upon any of the plurality of predictive models.