Dynamic routing of contact center requests

1. A method, comprising:

receiving, at a customer datacenter, a contact center request;

determining respective factors for available agents including agent-specific factors, environmental factors, and agent-cost factors;

obtaining, via a user interface, a configuration indicating:

respective first weights for the agent-specific factors,

respective second weights for the environmental factors; and

respective third weights for the agent-cost factors;

calculating respective agent routing scores for the available agents as respective weighted sums based on the respective first weights of the agent-specific factors, the respective second weights for the environmental factors, the respective third weights for the agent-cost factors, and the respective factors;

grouping the available agents into tiers based on the respective agent routing scores;

selecting, based on the tiers, at least one agent of the available agents; and

routing the contact center request to the at least one agent.

2. The method of claim 1 , wherein the user interface, is initially populated by machine-learning weights determined by a machine-learning model, and wherein the configuration overrides at least one of the machine-learning weights.

3. The method of claim 1 , further comprising:

selecting the at least one agent of the available agents based on a skill required for the contact center request.

4. The method of claim 3 , wherein the skill is language-based.

5. The method of claim 1 , wherein the agent-specific factors are based on survey data.

6. The method of claim 1 , wherein the environmental factors for the available agents are based on respective distances of respective agent devices of the available agents to a user device from which the contact center request is received.

7. A device, comprising:

a memory; and

a processor, the processor configured to execute instructions stored in the memory to:

receive, at a customer datacenter, a contact center request;

determine respective factors for available agents including agent-specific factors, environmental factors, and agent-cost factors;

obtain, via a user interface, a configuration indicating:

respective first weights for the agent-specific factors;

respective second weights for the environmental factors; and

respective third weights for the agent-cost factors;

calculate respective agent routing scores for the available agents as respective weighted sums based on the respective first weights of the agent-specific factors, the respective second weights for the environmental factors, the respective third weights for the agent-cost factors, and the respective factors;

group the available agents into tiers based on the respective agent routing scores;

select, based on the tiers, at least one agent of the available agents; and

route the contact center request to the at least one agent.

8. The device of claim 7 , wherein

the user interface, is initially populated by machine-learning weights determined by a machine-learning model, and wherein the configuration overrides at least one of the machine-learning weights.

9. The device of claim 7 , wherein the processor is further configured to execute instructions to:

select the at least one agent of the available agents based on a skill required for the contact center request.

10. The device of claim 7 , wherein the agent-specific factors are based on customer feedback data.

11. The device of claim 7 , wherein the agent-specific factors are based on survey data.

12. The device of claim 7 , wherein the environmental factors for the available agents are based on respective distances of respective agent devices of the available agents to a user device from which the contact center request is received.

13. A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations, comprising:

receiving, at a customer datacenter, a contact center request;

determining respective factors for available agents including agent-specific factors, environmental factors, and agent-cost factors;

obtaining, via a user interface, a configuration indicating:

respective first weights for the agent-specific factors;

respective second weights for the environmental factors; and

respective third weights for the agent-cost factors;

calculating respective agent routing scores for the available agents as respective weighted sums based on the respective first weights of the agent-specific factors, the respective second weights for the environmental factors, the respective third weights for the agent-cost factors, and the respective factors;

grouping the available agents into tiers based on the respective agent routing scores;

selecting, based on the tiers, at least one agent of the available agents; and

routing the contact center request to the at least one agent.

14. The non-transitory computer readable medium of claim 13 , wherein

the user interface, is initially populated by machine-learning weights determined by a machine-learning model.

15. The non-transitory computer readable medium of claim 13 , wherein the operations further comprise:

selecting the at least one agent of the available agents based on a skill required for the contact center request.

16. The non-transitory computer readable medium of claim 13 , wherein the agent-specific factors are based on survey data.

17. The non-transitory computer readable medium of claim 13 , wherein the environmental factors for the available agents are based on respective distances of respective agent devices of the available agents to a user device from which the contact center request is received.