Emotion Analyzer
InsuranceBusiness Impacts
Post Call Analysis
Ensure Scalability
Improve Customer Experience
Customer Key Facts
- Location : India
- Industry : Insurance
Problem Context
The client is a leader in the life insurance vertical offering individual and group insurance services. They were looking for a natural language and speech processing solution for keyword detection and to transcribe audio to text, perform sentiment analysis. This would help understand customer satisfaction, agent behavior, track the metrics around calls to improve the customer experience and build dashboards on top of this data. They wanted to improve the developed audio-based solution to perform sentiment analysis.
Challenges
- Building a specific solution for Indian English with abundant usage of Hindi was a challenge
- Lack of labeled data and thereby ensuring the quality of data tagging given the nature of real-life audio calls
- Security aspects w.r.t. PII sensitive data
- High diarization accuracies for mono format calls
Technologies
Amazon Transcribe
Amazon SageMaker
Amazon Quicksight
AWS Lambda
Amazon S3
Amazon Translate
Amazon ECR
Amazon Athena
Amazon Glue
Develop a Natural Language and Speech Processing Solution to Understand the Customer Satisfaction and Dashboards Tracking Customer Experience
Solution
Quantiphi is helping to create a robust transcribing solution with a scalable ML model to understand customer sentiments and develop dashboards in Quicksight to track the customer experience.
Result
- Set up and standardize a scalable process for evaluating customer satisfaction and agent performance
- Improve overall customer experience
- Create dashboards to take data based strategic decisions
