Assigning customer calls to customer care agents based on compatability
In one aspect, an example methodology implementing the disclosed techniques includes, in response to receipt at a call center of a call by a caller, generating a compatibility score for the caller, the compatibility score for the caller optimizes for caller satisfaction and potential upsell opportunities. The method also includes generating a compatibility score for individual agents available to handle the call, the compatibility score for the individual agents optimize for caller satisfaction and potential upsell opportunities. The method also includes matching the compatibility score for the caller to the compatibility scores for the individual agents and assigning an agent to the call based on the matching of the compatibility scores for the caller and the individual agents.
1. A computer implemented method to assign an agent to an incoming call to a call center, the method comprising:
in response to receipt at a call center of a call by a caller:
generating, using a machine learning (ML) model, a compatibility index for the caller, wherein the compatibility index is indicative of attributes of the caller;
generating an optimized raw compatibility index for the caller by applying a cost function to the compatibility index of the caller, wherein the cost function being solved to minimize dissatisfaction of the caller in handling of prior calls of the caller;
generating a compatibility score for the caller based on the optimized raw compatibility index of the caller;
generating, using the ML model, a compatibility index for individual agents available to handle the call, wherein the compatibility index for individual agents is indicative of attributes of the individual agent;
generating an optimized raw compatibility index for the individual agents based on the compatibility index of the individual agents, wherein the optimized raw compatibility index for the individual agents is indicative of prior call handling metrics of the individual agents;
generating a compatibility score for the individual agents based on the optimized raw compatibility index of the individual agents;
matching the compatibility score for the caller to the compatibility scores for the individual agents; and
assigning an agent to the call by applying a dining philosopher's problem to the compatibility scores for the caller and the individual agents.
2. The method of claim 1 , wherein assigning an agent to the call comprises assigning an agent having a compatibility score that matches the compatibility score of the caller to the call.
3. The method of claim 1 , wherein assigning an agent to the call comprises assigning an agent having a compatibility score that is closest to the compatibility score of the caller to the call.
4. The method of claim 1 , wherein generating the compatibility score for the caller comprises applying a cost function to maximize caller satisfaction and potential upsell opportunities.
5. The method of claim 1 , wherein generating the compatibility score for the individual agents comprises applying a cost function to maximize caller satisfaction and potential upsell opportunities.
6. A system comprising:
one or more non-transitory machine-readable mediums configured to store instructions; and
one or more processors configured to execute the instructions stored on the one or more non-transitory machine-readable mediums, wherein execution of the instructions causes the one or more processors to, responsive to receipt at a call center of a call by a caller:
generate, using a machine learning (ML) model, a compatibility index for the caller, wherein the compatibility index is indicative of attributes of the caller;
generate an optimized raw compatibility index for the caller by applying a cost function to the compatibility index of the caller, wherein the cost function being solved to minimize dissatisfaction of the caller in handling of prior calls of the caller;
generate a compatibility score for the caller based on the optimized raw compatibility index of the caller;
generate, using the ML model, a compatibility index for individual agents available to handle the call, wherein the compatibility index for individual agents is indicative of attributes of the individual agent;
generate an optimized raw compatibility index for the individual agents based on the compatibility index of the individual agents, wherein the optimized raw compatibility index for the individual agents is indicative of prior call handling metrics of the individual agents;
generate a compatibility score for the individual agents based on the optimized raw compatibility index of the individual agents;
match the compatibility score for the caller to the compatibility scores for the individual agents; and
assign an agent to the call by applying a dining philosopher's problem to the compatibility scores for the caller and the individual agents.
7. The system of claim 6 , wherein to assign an agent to the call comprises to assign an agent having a compatibility score that matches the compatibility score of the caller to the call.
8. The system of claim 6 , wherein to assign an agent to the call comprises to assign an agent having a compatibility score that is closest to the compatibility score of the caller to the call.
9. The system of claim 6 , wherein to generate the compatibility score for the caller or the individual agents comprises to apply a cost function to maximize caller satisfaction and potential upsell opportunities.
10. A computer program product including one or more non-transitory machine-readable mediums encoding instructions that when executed by one or more processors cause a process to be carried out for assigning an agent to an incoming call to a call center, the process comprising:
in response to receipt at a call center of a call by a caller:
generating, using a machine learning (ML) model, a compatibility index for the caller, wherein the compatibility index is indicative of attributes of the caller;
generating an optimized raw compatibility index for the caller by applying a cost function to the compatibility index of the caller, wherein the cost function being solved to minimize dissatisfaction of the caller in handling of prior calls of the caller;
generating a compatibility score for the caller based on the optimized raw compatibility index of the caller;
generating, using the ML model, a compatibility index for individual agents available to handle the call, wherein the compatibility index for individual agents is indicative of attributes of the individual agent;
generating an optimized raw compatibility index for the individual agents based on the compatibility index of the individual agents, wherein the optimized raw compatibility index for the individual agents is indicative of prior call handling metrics of the individual agents;
generating a compatibility score for the individual agents based on the optimized raw compatibility index of the individual agents;
matching the compatibility score for the caller to the compatibility scores for the individual agents; and
assigning an agent to the call by applying a dining philosopher's problem to the compatibility scores for the caller and the individual agents.
11. The computer program product of claim 10 , wherein assigning an agent to the call comprises assigning an agent having a compatibility score that matches the compatibility score of the caller to the call or assigning an agent having a compatibility score that is closest to the compatibility score of the caller to the call.
12. The computer program product of claim 10 , wherein generating the compatibility score for the caller or the individual agents comprises applying a cost function to maximize caller satisfaction and potential upsell opportunities.