Relative-Gain Predictive Routing for Contact Center Agent Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing contact center systems struggle to optimize the routing of interactions to agents efficiently, leading to suboptimal service quality and increased costs due to the high labor costs of live agents and inefficiencies in automated processes.
Innovation Solution
A system and method for predictive routing that leverages relative gain by determining a predictive routing score and relative gain for each agent based on historical performance, interaction class, and agent value, ranking agents accordingly, and selecting the most optimal agent for the interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional routing mechanisms are used to route interactions to agents, then the system is simple to operate, but service quality is suboptimal and operational costs are high
Solution Approach 1:
The system pre-calculates predictive routing scores for multiple prospective agents before routing an interaction, based on historical performance data and interaction characteristics. This preliminary scoring enables optimized routing decisions without real-time computational complexity, improving service quality while maintaining operational simplicity.
Solution Approach 2:
The system creates a virtual model of agent performance by calculating predictive routing scores that replicate historical performance patterns. This scoring model acts as a copy of actual agent capabilities, enabling optimized routing decisions without directly observing real-time agent performance, thus improving service quality without proportionally increasing system complexity.
2Reliability
If more live agents are deployed to improve service quality, then service quality improves, but operational costs increase due to high labor costs
Solution Approach 1:
The system changes the routing parameter from simple availability-based assignment to predictive routing scores that incorporate historical performance, interaction class, and relative gain metrics. This parameter transformation enables more efficient agent utilization, improving service quality while reducing the number of agents needed and thereby lowering operational costs.
Solution Approach 2:
The system uses historical performance data as feedback to continuously improve routing decisions. By analyzing past interaction outcomes and agent performance, the predictive routing score adjusts future routing assignments to maximize service quality while minimizing resource consumption, effectively reducing operational costs.
3Loss of energy
If automated processes are used to reduce labor costs, then operational costs decrease, but inefficiencies arise leading to suboptimal service quality
Solution Approach 1:
The predictive routing score acts as an intermediary between automated routing processes and human agent capabilities. It translates historical performance data and interaction characteristics into optimized routing decisions, enabling automated processes to achieve service quality comparable to or better than manual routing while maintaining low operational costs.
4Productivity
If interactions are routed based on basic availability, then routing is simple, but wait times are increased and efficiency is reduced
Solution Approach 1:
The system pre-calculates predictive routing scores for prospective agents based on historical performance and interaction characteristics before routing decisions are made. This preliminary computation enables efficient routing that reduces wait times and improves productivity without requiring complex real-time calculations, maintaining system simplicity.
Solution Approach 2:
The routing system dynamically adjusts agent selection based on predictive routing scores that reflect current agent performance and interaction requirements. This dynamic approach optimizes routing decisions for each interaction, improving contact center efficiency while the pre-calculated scoring mechanism keeps the implementation manageable.
Data Source
AI summary
A method of routing interactions to contact center agents according to an embodiment includes identifying an interaction to be routed to a contact center agent, determining a predictive routing score for each prospective contact center agent to which the interaction can be routed based on a historical performance of each prospective agent, determining a relative gain for each prospective agent based on an interaction class of the interaction, an agent class performance of the prospective agent, and an agent value of the prospective agent, wherein the relative gain of a respective agent is indicative of a relative optimization improvement of routing the interaction to the respective agent relative to another of the prospective agents, ranking the prospective agents based on the associated predictive routing score and the associated relative gain for each prospective agent, and routing the interaction to an agent selected based on the ranking of the prospective agents.