Call Routing via Life Event Probability Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern businesses face inefficiencies in routing customer calls to appropriate customer service representatives due to the complexity and diversity of services offered, leading to cumbersome and time-consuming processes, especially when dealing with customer-specific data related to life events.
Innovation Solution
A system and method that utilize a customer's data fingerprint, comprising life event entries, to apply to history-based statistical models, generating probability scores for routing customers to the most suitable representatives, thereby streamlining the call routing process without requiring extensive customer interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional call routing methods are used, then customers are connected to customer service representatives, but the routing process is cumbersome and time-consuming due to business diversity and lack of customer-specific data utilization
Solution Approach 1:
The system performs preliminary actions by collecting and storing customer-specific data (life events, service interactions, preferences) in advance in a database. When a call arrives, the pre-stored data is immediately retrieved and processed through statistical models to determine optimal routing, eliminating the need for time-consuming real-time data collection and enabling instant intelligent routing decisions
Solution Approach 2:
The system changes the routing parameters from generic business-unit-based routing to customer-specific probability-based routing. By applying history-based statistical models to customer data, the system generates probability scores that dynamically determine routing decisions, transforming the routing process from static and manual to dynamic and automated based on individual customer characteristics
2Measurement precision
If customer-specific data is utilized for routing, then routing accuracy improves, but system complexity increases due to data processing requirements
Solution Approach 1:
The system introduces an intermediary layer consisting of history-based statistical models that process customer data. These models act as mediators between the raw customer data in the database and the routing decision, automatically analyzing life events and service history to generate probability scores. This intermediary processing layer simplifies the overall system architecture by automating the complex data analysis that would otherwise require manual intervention or overly complicated routing logic
Data Source
AI summary
A method of routing a customer to a desired representative of a call center includes, in accordance with an embodiment of the present disclosure, receiving a communication from the customer. The method also includes identifying, within a database saved to a server, a customer account associated with the customer, and identifying data indicative of one or more life event entries saved to the customer account and corresponding with one or more life events of the customer. The method also includes applying the identified data indicative of the one or more life event entries to a history-based statistical models, where each history-based statistical model represents a corresponding call routing channel. The method also includes assigning a probability score for each history-based statistical model, where each probability score represents a likelihood that the corresponding call routing channel represented by the history-based statistical model is desired by the customer. The method also includes routing, via a switch, the customer to the desired representative via the call routing channel associated with the desired representative.