Incoming Call Handling With ML-Guided Self-Service Queues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large corporate entities face increased human advisor workloads and longer client wait times due to the growing volume and complexity of client inquiries, particularly in environments with static advisor numbers.
Innovation Solution
Implementing a system that uses trained machine learning models to identify self-serve actions during client calls, allowing clients to complete these actions while waiting in a virtual queue, thereby reducing the need for human advisor assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of human advisors remains static, then the operational cost is controlled, but the client wait times increase and advisor workloads increase
Solution Approach 1:
The system enables clients to perform self-service actions during their wait time in the virtual queue. Clients can complete actions such as updating profile information, checking account details, or initiating transactions independently through the automated system, thereby reducing the burden on human advisors and decreasing actual handle time without increasing advisor headcount.
Solution Approach 2:
The system identifies and prepares self-service actions for clients before they are connected to human advisors. By pre-identifying actionable items through machine learning analysis of call data, the system allows clients to complete preparatory tasks during waiting periods, so that when human advisors do intervene, the interactions are more efficient and shorter in duration.
2Productivity
If human advisors handle all client inquiries, then client needs are met, but advisor workload increases and handling time increases
Solution Approach 1:
Clients are empowered to complete certain actions independently through the automated system during their wait time. This self-service capability reduces the number of tasks that require human advisor intervention, thereby decreasing overall advisor handling time and increasing productivity without compromising client service quality.
Solution Approach 2:
The automated system acts as an intermediary between clients and human advisors. It handles routine information gathering, action identification, and client guidance, thereby filtering out tasks that can be completed autonomously and leaving only complex issues for human advisors, which optimizes their workload and reduces handling time.
3Loss of time
If more advisors are hired to handle increased client volume, then client service quality improves, but operational cost increases
Solution Approach 1:
By implementing self-service capabilities that allow clients to complete actions during their wait time, the system reduces the actual handle time required for each interaction. This enables the same number of advisors to handle more clients effectively, or reduces the need to hire additional advisors to maintain service quality during high-volume periods.
Solution Approach 2:
The system performs preliminary identification and preparation of self-service actions before human advisor intervention is needed. This preliminary processing reduces the complexity and duration of human advisor interactions, allowing existing advisors to maintain higher productivity levels without requiring additional headcount to manage increased client volume.
Data Source
AI summary
A method of handling an incoming call from a client includes receiving call data, the voice data including at least voice data generated based on the client's voice during the call. The call data is processed to identify, using at least one trained machine learning model, at least one first action that can be completed during the call by the client without assistance from a human advisor. The client is invited to complete the at least one first action.