Predictive Call Routing Using Statistical Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current call routing systems in contact centers rely solely on business rules, which may not accurately determine the required skill set and proficiency level for customer service representatives, leading to inefficient routing of calls and increased waiting times for customers.
Innovation Solution
A predictive call routing system that uses statistical modeling to analyze caller parameters and generate scores for various actions, selecting the most appropriate representative based on skill sets and proficiency levels, and updating models based on feedback for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional business rules are used for call routing, then the routing process is simple and fast, but the accuracy of determining required skill set and proficiency level is insufficient
Solution Approach 1:
The system performs preliminary statistical analysis on historical call data to build predictive models before actual call routing occurs. These models pre-calculate the relationship between caller parameters and required representative skills, enabling accurate skill determination when calls are actually routed without real-time computational complexity
Solution Approach 2:
Statistical models serve as intermediaries between the simple business rules and the complex task of skill determination. The models translate caller parameters into predicted skill requirements and proficiency levels, bridging the gap between simple routing logic and accurate skill matching
2Loss of time
If calls are routed based on predefined business rules, then the routing process is quick, but customers experience increased waiting times due to multiple transfers
Solution Approach 1:
The system performs preliminary analysis of caller parameters and predicts the most appropriate representative and required skills before the call is actually routed. This pre-determination eliminates the need for multiple transfers and hold times, as the correct representative is identified in advance
Solution Approach 2:
The system uses feedback from historical call outcomes to continuously refine its statistical models. By analyzing which representatives successfully resolved customer issues and which required transfers, the system learns to make more accurate routing decisions, reducing waiting times over time
3Measurement precision
If statistical modeling is implemented for predictive routing, then routing accuracy improves, but system complexity increases
Solution Approach 1:
Complex statistical modeling is performed in advance during an offline training phase using historical call data. Once the models are trained, they can be deployed with minimal real-time computational overhead, achieving high routing accuracy without burdening the live call routing system
Solution Approach 2:
The system segments the routing process into distinct phases: offline model training using historical data, real-time parameter extraction from incoming calls, and model-based prediction for routing decisions. This segmentation allows complex analytical work to be done separately from time-critical routing operations
Data Source
AI summary
A predictive call routing system that includes a real-time decision engine to receive information about a customer and identify a skill that is useful for providing service to the caller. The decision engine identifies the skill by generating scores for a plurality of statistical models using the statistical models and parameters associated with the caller, each statistical model representing a correlation between a subset of parameters and an action that may be performed or requested to be performed by the caller, the score for each statistical model being generated using the statistical model and the subset of parameters associated with the statistical model, and identifies a skill based on the scores. The system includes a call router to route a call from the customer to a representative who has the skill.