Revolutionizing Customer Service with AI: A Case Study of Intact Financial Corporation
Intact Financial Corporation, the leading provider of property and casualty insurance in Canada, faced a challenge in managing its vast network of customer support call centers. With up to 20,000 calls per day, the manual auditing process was inefficient. To address this, Intact turned to AI and speech-to-text technology and developed an automated solution called Call Quality (CQ) using AI services from Amazon Web Services (AWS).
Amazon Transcribe, a fully managed automatic speech recognition service, played a key role in improving critical KPIs with AI-powered contact center call auditing and analytics. The CQ solution enabled Intact to handle 1,500% more calls, reduce agent handling time by 10%, and generate valuable insights about agent behavior.
Enhancing Call Analytics with Speech-to-Text and Machine Learning
Intact aimed to develop a cost-effective and efficient call analytics platform for their contact centers by using speech-to-text and machine learning technologies. Amazon Transcribe was chosen for its accuracy, adaptability to diverse business needs, scalability, and deep learning capabilities.
Intact’s call processing workflow incorporated custom ML models for components identification, sentiment analysis, and more. The implementation led to a 1,500% increase in auditing speed and a 10% reduction in agents’ time per call.
Automating Model Deployment with MLOps
Intact built an automated MLOps pipeline using AWS services for ML experiment tracking, model deployment, and capacity planning. This pipeline reduced the delivery time of new ML models, making auditors 65% more efficient.
Empowering Call Quality Agents with Robust Frontend and API
The CQ application offered a powerful search interface and trend dashboards tailored for call quality agents. Using Amazon OpenSearch Service, Amazon Cognito, and Lambda functions, the application provided insights on call handle time, speech time vs. silence time, and more.
Driving Efficiency and Productivity with AI
The implementation of the new system at Intact Financial Corporation resulted in a significant increase in efficiency and productivity. The MLOps pipeline reduced the delivery time of new ML models, making auditors more efficient. Additionally, the solution provided intangible benefits such as high availability and robust deployments with a near-zero failure rate.
Conclusion
In conclusion, Intact Financial Corporation’s implementation of the CQ, powered by AWS AI services, has revolutionized their customer service approach. This case study showcases the transformative power of AI and speech-to-text technology in enhancing customer service efficiency and effectiveness. The journey of Intact Financial Corporation exemplifies the potential of AI to drive significant improvements in service delivery and customer satisfaction.
About the Authors
Étienne Brouillard is an AWS AI Principal Architect at Intact Financial Corporation.
Ami Dani is a Senior Technical Program Manager at AWS focusing on AI/ML services.
Prabir Sekhri is a Senior Solutions Architect at AWS in the enterprise financial services sector.