Call Routing via Predictive Value Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional call center routing methods often lead to high business value callers being subjected to long waits, while low business value calls are prioritized, due to inefficiencies in identifying and routing inbound callers based on their value, leading to dissatisfaction and inefficient allocation of resources.
Innovation Solution
The implementation of a predictive machine learning model that uses customer identifiers such as name, street address, and phone number to analyze and route inbound callers, employing n-gram modeling and approximate string matching techniques to prioritize calls based on predicted value, with the Polymr search engine indexing and retrieving customer data for real-time scoring and routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional first-come-first-served routing is used, then all callers are treated equally, but high business value callers are subjected to long waits causing dissatisfaction
Solution Approach 1:
The system changes the routing parameter from simple queue position to a composite score that incorporates predicted business value, caller identification confidence, and historical interaction data. This allows high-value callers to be prioritized while maintaining fair treatment for all callers.
Solution Approach 2:
The system performs preliminary customer identification and value assessment during the call setup phase using automated telephone identification systems and predictive analytics models, rather than waiting until the caller reaches the front of the queue. This preliminary action enables proactive routing decisions that reduce wait times for high-value callers.
2Productivity
If automated call routing with real-time data processing is implemented, then high business value callers can be identified and prioritized, but errors in customer identification occur leading to routing inefficiencies
Solution Approach 1:
The system implements feedback loops where routing outcomes and customer identification results are continuously monitored and used to refine predictive models. When identification errors occur, the system learns from these errors and adjusts its algorithms to improve future accuracy, balancing speed with precision.
Solution Approach 2:
The system prepares multiple potential routing options and validation checks in advance. When customer identification is uncertain, pre-configured fallback procedures and manual verification protocols are ready to prevent erroneous routing decisions, cushioning against the impact of identification errors.
3Reliability
If manual routing processes are used, then callers can be personally assessed, but the process becomes burdensome and time-consuming
Solution Approach 1:
The system enables automated self-service routing where callers are automatically identified, assessed, and routed based on their predicted business value and caller ID data without requiring manual agent intervention. This maintains accurate routing decisions while eliminating the time burden of manual processes.
Solution Approach 2:
The system replaces manual mechanical routing processes with automated electronic identification and predictive analytics systems. Computer-based algorithms analyze caller data and make routing decisions that previously required human judgment, dramatically reducing processing time while maintaining or improving routing accuracy.
4Ease of operation
If round-robin routing is implemented, then all agents receive equal call distribution, but limited call center resources are not optimally allocated to high business value callers
Solution Approach 1:
The system applies different routing qualities to different callers based on their predicted business value. High-value callers receive prioritized routing to top-performing agents, while standard callers receive equitable distribution. This local differentiation optimizes resource allocation without sacrificing operational simplicity.
Solution Approach 2:
The routing system dynamically adjusts agent assignments based on real-time performance data and caller value assessments. Agents who demonstrate higher effectiveness with certain caller types are dynamically assigned more high-value calls, optimizing resource allocation while maintaining ease of operation through automated dynamic scheduling.
Data Source
AI summary
A call management system of a call center identifies an inbound caller based upon computer analysis of customer identifiers, which may include at least two of customer name, street address, and zip code. Approximate string matching analysis matches n-grams generated from strings within customer identifiers, with n-grams generated from customer identification fields while searching one or more databases. Approximate string matching can incorporate a closeness metric based on Jaccard distance, and a Gaussian mixture model of best matches. In one embodiment, a Polymr search engine analyzes customer identifiers of inbound callers to retrieve customer data, such as customer demographic data, matched to the customer identifiers. In another embodiment, the Polymr search engine analyzes customer identifiers of inbound callers to identify repeat callers and retrieve previously collected customer data. Retrieved customer data is used in predictive modeling and scoring value of the inbound call, and in routing the scored inbound call.