Genuineness Opinion Score Model for Contact Center Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact center systems lack the ability to verify the genuineness of customer feedback before agent performance evaluation, leading to potential misassignment of coaching plans and inefficient resource allocation due to non-genuine feedback.
Innovation Solution
A machine learning model, Genuineness Opinion Score (GOS) model, is developed to filter out non-genuine customer feedback by processing interaction metadata and historical data through data manipulation, visualization, and feature augmentation phases, using a multiple linear regression algorithm to generate a GOS score and filter out non-genuine feedback before evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If customer feedback is used for agent performance evaluation without verification, then evaluation coverage is improved, but reliability of evaluation deteriorates due to non-genuine feedback
Solution Approach 1:
The system performs preliminary verification of customer feedback genuineness using a machine learning model before the feedback is used for agent performance evaluation. This preliminary action filters out non-genuine feedback in advance, ensuring that only verified genuine feedback reaches the evaluation stage, thus maintaining both high evaluation coverage and reliability
Solution Approach 2:
A machine learning model acts as an intermediary between customer feedback collection and agent performance evaluation. This intermediary layer analyzes feedback genuineness and determines whether feedback should be included in evaluation, preventing non-genuine feedback from affecting evaluation reliability while preserving genuine feedback for comprehensive evaluation coverage
2Loss of information
If all customer feedback is processed for evaluation, then completeness of assessment is improved, but loss of time increases due to processing non-genuine feedback
Solution Approach 1:
The system extracts and removes non-genuine feedback from the feedback stream before it enters the performance evaluation process. By taking out only the relevant genuine feedback for evaluation, the system maintains complete assessment of agent performance based on valid data while significantly reducing the time spent processing and analyzing non-genuine feedback
Solution Approach 2:
The machine learning model performs preliminary filtering of feedback genuineness before the time-consuming evaluation process begins. This preliminary action identifies and separates genuine feedback from non-genuine feedback, ensuring that evaluation resources are spent only on genuine feedback, thus maintaining assessment completeness while minimizing time loss
3Reliability
If machine learning model is implemented to verify feedback, then reliability of feedback determination is improved, but device complexity increases
Solution Approach 1:
The machine learning model is trained on historical feedback data and interaction metadata to automatically determine feedback genuineness without requiring manual verification. The system serves itself by continuously learning from past data and improving its verification accuracy, achieving high reliability in feedback determination while keeping operational complexity low through automation
Solution Approach 2:
The manual or mechanical process of verifying feedback genuineness is replaced with an automated machine learning model that analyzes feedback patterns, interaction metadata, and historical data. This substitution eliminates the need for manual verification efforts while providing consistent, reliable determination of feedback authenticity, improving reliability without proportionally increasing operational complexity
Data Source
AI summary
A computerized-method for generating a machine-learning model to determine genuineness of customer feedback to filter-out, non-genuine agent recording segments from evaluation. The computerized-method includes generating a Genuineness Opinion Score (GOS) model. The generating of GOS model includes: (a) a data manipulation phase; (b) a data visualization and analysis phase, and (c) a feature augmentation phase for sorting the variables in a set of unique and relevant variables into two categories: estimated variables and anticipated variables. The estimated variables are used for calculation of a GOS of an interaction that is received in a contact center and the anticipated variables are used for calculation of a threshold of said GOS.