System and method for managing customer call-backs

• US 10,582,060 B1
• Filed: 04/08/2019
• Issued: 03/03/2020
• Est. Priority Date: 08/29/2017
• Status: Active Grant

• Current Assignee: Massachusetts Mutual Life Insurance Company
• Original Assignee: Massachusetts Mutual Life Insurance Company
• Inventors: Merritt, Sears
• Primary Examiner(s): Hoque, Nafiz E
• Application Number:
  US16/378,248
• Time in Patent Office: 330 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 2203/558 Databases
• CPC Class Codes: H04M 3/42059 Making use of the calling party identifier
• CPC Class Codes: H04M 3/42195 Arrangements for calling back a calling subscriber when the wanted subscriber ceases to be busy H04M3/48
• CPC Class Codes: H04M 3/4365 based on information specified by the calling party, e.g. priority or subject
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04M 3/5231 with call back arrangements
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 3/5235 Dependent on call type or called number [DNIS]

Abstract

A system herein provides automated call-back of customers who have terminated an inbound call by exercising a call-back option of an interactive voice response unit or by abandoning the inbound call, using predictive modeling of caller value to prioritize call-backs. The call management system monitors the inbound customer call and detects any termination of the customer call. A call-back module opens a call-back record for the terminated customer call and associates that call-back record with an identified customer. The call-back module retrieves customer demographic data and other data associated with the identified customer. A predictive module determines a value prediction signal for the identified customer by modeling purchase and lapse behaviors and classifies each identified customer for either priority call-back or subordinate call-back treatment. Priority call-back classification may result in assignment to a priority call-back queue, assignment to a priority call-back queue position, or call-back by a selected agent.

Claims

1. A processor based method for managing customer calls within a call center, comprising:

in response to receiving a customer call from an identified customer at an inbound call receiving device;

opening, by a processor, an inbound call record for the customer call including any automatic number identifier information delivered with the customer call;

monitoring, by the processor, the customer call of the identified customer to retrieve interactive voice response (IVR) data received from the identified customer via interaction with an IVR unit, and updating the inbound call record for the identified customer with IVR data retrieved;

detecting, by the processor, a termination of the customer call;

in the event of detecting the termination of the customer call;

executing, by the processor, a predictive machine learning model configured to determine a value prediction signal representative of a likelihood that the identified customer will accept an offer for a product purchase, by inputting information from the inbound call record for the customer call the call-back record for the identified customer into a logistic regression model operating in conjunction with a tree based model;

classifying, by the predictive model executing on the processor based on the value prediction signal determined by the predictive model, the identified customer into one of a first value group and a second value group;

in the event the classifying step classifies the identified customer into the first value group, assigning, by the processor, the identified customer to a priority call-back queue assignment;

in the event the classifying step classifies the identified customer into the second value group, assigning, by the processor, the identified customer to a subordinate call-back queue assignment; and

automatically calling back the identified customer, by an automatic calling device in communication with the processor, based on the priority call-back queue assignment or the subordinate call-back queue assignment for the identified customer.

2. The processor based method of claim 1, wherein the predictive machine-learning model is continually trained by inputting updated customer demographic data, payment data, marketing costs data, and lapse data into the logistic regression model operating in conjunction with a tree based model.

3. The processor based method of claim 1, further comprising the step of opening, by the processor, a call-back record for the terminated customer call including any automatic number identifier information delivered and any IVR data in the inbound call record, wherein the executing step inputting the call-back record for the terminated customer call into the logistic regression model operating in conjunction with the tree based model.

4. The processor based method of claim 3, further comprising the step, after opening the call-back record for the terminated customer call, of retrieving customer demographic data associated with the identified customer;

wherein the predictive machine learning model is configured to determine the value prediction signal by inputting the call-back record for the identified customer and the customer demographic data associated with the identified customer into the logistic regression model operating in conjunction with the tree based model.

5. The processor based method of claim 3, further comprising the step, after opening the call-back record for the terminated customer call, of retrieving call history information associated with the identified customer;

wherein the predictive machine learning model is configured to determine the value prediction signal by inputting the call-back record for the identified customer and the call history information associated with the identified customer into the logistic regression model operating in conjunction with the tree based model.

6. The processor based method of claim 5, wherein the automatically calling back the identified customer by the automatic calling device based the priority call-back queue assignment comprises call-back by a selected agent of the call center, wherein the selected agent is selected based on the call history information associated with the identified customer.

7. The processor based method of claim 1, wherein the detecting step comprises detecting any termination of the customer call by exercising a call-back option via the interactive voice response unit or by abandoning the customer call, wherein the identified customer is associated with one or more of an ANI or DNIS delivered with the customer call, and a call-back number provided by the inbound caller while exercising the call-back option.

8. The processor based method of claim 1, wherein the step of monitoring the customer call of the identified customer further updates the inbound call record with inbound queue data retrieved by monitoring an inbound call queue including the identified customer, and the step of opening the call-back record for the terminated customer call further includes in the call-back record any inbound queue data in the inbound call record.

9. The processor based method of claim 8, wherein the inbound queue data include one or more of waiting time of the customer call spent in the inbound queue, and identity of the inbound queue among multiple inbound queues of the call center.

10. The processor based method of claim 1, wherein the priority call-back queue assignment is a queue position in a priority call-back queue, and the subordinate call-back queue assignment is a queue position in a subordinate call-back queue.

11. The processor based method of claim 10, wherein the priority call-back queue is a queue for immediate call-back, and the subordinate call-back queue is a queue for deferred call-back.

12. The processor based method of claim 10, wherein the priority call-back queue is a queue for call-back by higher-skill agents, and the subordinate call-back queue is a queue for call-back by lower-skill agents.

13. The processor based method of claim 1, wherein the automatically calling back the identified customer by the automatic calling device based the priority call-back queue assignment comprises call-back by a selected agent of the call center.

14. The processor based method of claim 13, wherein the selected agent of the call center is selected by matching customer identifier data to private call-back data associated with the selected agent.

15. A system for managing customer calls within a call center, comprising:

an inbound telephone call receiving device for receiving a customer call from an inbound caller to the call center;

a telephone calling device for placing outbound customer calls from the call center;

an interactive voice response unit;

a predictive modeling module that stores a predictive model of customer value, wherein the predictive model comprises a logistic regression model operating in conjunction with a tree based model; and

a processor, configured to execute a call-back management module, wherein the processor in communication with the non-transitory machine-readable memory and the predictive modeling module executes a set of instructions instructing the processor to;

generate an inbound call record including any automatic number identifier information delivered with the customer call received by the inbound telephone call receiving device;

monitor the customer call to detect a termination of the customer call, and in the event of detecting the termination of the customer call;

open a call-back record for the terminated customer call and input the call-back record into the predictive modeling module;

determine a value prediction signal representative of representative of a likelihood that the identified customer will accept an offer for a product purchase;

classify the identified customer into one of a first value group and a second value group based on the value prediction signal; and

direct the telephone calling device for placing outbound customer calls;

in the event the call-back management module classifies the identified customer into the first value group, to automatically call back the identified customer based on a priority call-back queue assignment;

in the event the call-back management module classifies the identified customer into the second value group, to automatically call back the identified customer based on a subordinate call-back queue assignment.

16. The system according to claim 15, wherein the set of instructions further comprise an instruction to retrieve customer demographic data associated with the identified customer and input the retrieved customer demographic data into the predictive modeling module.

17. The system according to claim 15, wherein the predictive machine-learning model is continually trained by inputting updated customer demographic data, payment data, marketing costs data, and lapse data into the logistic regression model operating in conjunction with a tree based model.

18. The system according to claim 15, further comprising non-transitory machine-readable memory that stores call history information for customers of the call center, wherein the set of instructions further comprise an instruction to retrieve from the non-transitory machine-readable memory any of the call history information associated with the identified customer and input the retrieved call history information into the predictive modeling module.

19. The system according to claim 15, wherein the priority call-back queue assignment is a queue position in a priority call-back queue, and the subordinate call-back queue assignment is a queue position in a subordinate call-back queue.

20. The system according to claim 15, wherein priority call-back queue assignment comprises call-back by a selected agent of the call center.