Predicted call time as routing variable in a call routing center system
View Patent ↗Systems and processes are disclosed for routing callers to agents in a contact center based on predicted call handle times. An exemplary process includes using predicted call handle time as a variable for call routing along with a performance matching and/or psychodemograhpic matching process of caller-agent pairs to maximize sales, customer satisfaction, and so on. The process may allocate the highest performing agents and/or the most “demographic matchable” agents to those callers that are predicted have the shortest duration. The process may further allocate the lowest performing agents and or the least “demographic matchable” agents to those callers that are predicted have the longest duration, or may not allocate the lowest performing agents to any callers at all.
1. A computer-implemented method for routing callers to agents in a call-center routing environment, the method comprising:
determining, by one or more computers, a respective estimated call handle time for each caller of a set of callers based at least in part on demographic data of the respective caller;
grouping, by the one or more computers, the set of callers into two or more subgroups comprising one handle time subgroup and a lower handle time subgroup relative to the one handle time subgroup based at least in part on the respective estimated handle times for the respective callers;
obtaining, by the one or more computers, a respective ranking or score for a given outcome variable for each agent of a set of agents;
grouping, by the one or more computers, the set of agents into two or more subgroups comprising one ranking or score subgroup and a lower ranking or score subgroup relative to the one ranking or score subgroup based at least in part on the respective rankings or scores for the respective agents; and
matching, by the one or more computers, the respective callers in the one handle time subgroup to respective of the agents in the lower ranking or score subgroup, and the respective callers in the lower handle time subgroup to respective of the agents in the one ranking or score subgroup.
2. The computer-implemented method of claim 1 , wherein the given outcome variable is associated with a sales rate.
3. The computer-implemented method of claim 1 , wherein the given outcome variable is an estimated call handle time for the agent.
4. The computer-implemented method of claim 1 , further comprising comparing, by the one or more computers, demographic data of the set of agents to demographic data of the set of callers via a pattern matching algorithm to determine the chance of a positive result for at least the given outcome variable, wherein matching the callers to the agents is further based on results of the comparison.
5. The computer-implemented method of claim 1 , wherein the estimated call handle time for a caller is determined based at least in part on the age of the caller.
6. A non-transitory computer readable storage medium comprising computer-readable instructions for matching, when executed by one or more computers, callers to agents in a call-center routing environment based on estimated call handle time, the computer readable instructions comprising:
determining, by the one or more computers, a respective estimated call handle time for each caller of a set of callers based at least in part on demographic data of the respective caller;
grouping, by the one or more computers, the set of callers into two or more subgroups comprising one handle time subgroup and a lower handle time subgroup relative to the one handle time subgroup based at least in part on the respective estimated handle times for the respective callers;
obtaining, by the one or more computers, a respective ranking or score for a given outcome variable for each agent of a set of agents;
grouping, by the one or more computers, the set of agents into two or more subgroups comprising one ranking or score subgroup and a lower ranking or score subgroup relative to the one ranking or score subgroup based at least in part on the respective rankings or scores for the respective agents; and
matching, by the one or more computers, the respective callers in the one handle time subgroup to respective of the agents in the lower ranking or score subgroup, and the respective callers in the lower handle time subgroup to respective of the agents in the one ranking or score subgroup.
7. The computer readable storage medium of claim 6 , wherein the given outcome variable is associated with a sales rate.
8. The computer readable storage medium of claim 6 , wherein the given outcome variable is an estimated call handle time for the agent.
9. The computer readable storage medium of claim 6 , further comprising program code for comparing demographic data of the set of agents to demographic data of the set of callers via a pattern matching algorithm to determine the chance of a positive result for at least the given outcome variable, wherein matching the callers to the agents is further based on results of the comparison.
10. The computer readable storage medium of claim 6 , wherein the estimated call handle time for a caller is determined based at least in part on the age of the caller.
11. A system for routing callers to agents in a call center routing environment based on estimated call handle time, the apparatus comprising:
one or more computers configured with computer-readable program code to perform, when executed, the steps:
determining, by one or more computers, a respective estimated call handle time for each caller of a set of callers based at least in part on demographic data of the respective caller;
grouping, by the one or more computers, the set of callers into two or more subgroups comprising one handle time subgroup and a lower handle time subgroup relative to the one handle time subgroup based at least in part on the respective estimated handle times for the respective callers;
obtaining, by the one or more computers, a respective ranking or score for a given outcome variable for each agent of a set of agents;
grouping, by the one or more computers, the set of agents into two or more subgroups comprising one ranking or score subgroup and a lower ranking or score subgroup relative to the one ranking or score subgroup based at least in part on the respective rankings or scores for the respective agents; and
matching, by the one or more computers, the respective callers in the one handle time subgroup to respective of the agents in the lower ranking or score subgroup, and the respective callers in the lower handle time subgroup to respective of the agents in the one ranking or score subgroup.
12. The system of claim 11 , wherein the given outcome variable is associated with a sales rate.
13. The system of claim 11 , wherein the one or more computers are further configured with program code, to perform, when executed, the step of determining an estimated call handle time for the agent, wherein matching the caller to the agent of the set of agents is further based on the estimated call handle time for the agent.
14. The system of claim 11 , wherein the one or more computers are further configured with program code, to perform, when executed, the step of comparing demographic data of the set of agents to demographic data of the set of callers via a pattern matching algorithm to determine the chance of a positive result for at least the given outcome variable, wherein matching the callers to the agents is further based on results of the comparison.
15. The system of claim 11 , wherein the estimated call handle time for a caller is determined based at least in part on the age of the caller.