State Auto Improves Processes across the Life Cycle Using AWS Machine Learning, Computer Vision, and Serverless Architecture


State Automobile Mutual Insurance Company (State Auto) wanted to better understand and anticipate the requirements of its customers to provide them with the information they needed before they even knew to ask for it. The company began using technology to help its customer service representatives (CSRs) meet quality and customer satisfaction score goals when it built its SA360 solution on Amazon Web Services (AWS). By using data-fueled insights and making these insights available to customers and CSRs, State Auto was able to build a better service experience, redirecting typical customer calls to self-service channels so that CSRs were able to focus on those customers with more complex needs. Following the success of this project, State Auto began using more AWS services, including machine learning (ML), computer vision, and serverless services, to help further its goals in other areas such as the automation of the underwriting processes and early detection of fraudulent claims to expedite case review.

Multiethnic colleagues sitting at desk looking at laptop computer in office.

Because AWS services do their job so well out of the box, we have the flexibility to be creative and build things on top of them."

Uthra Ramanujam
Vice President of Strategic Technology Research, State Automobile Mutual Insurance Company

Exploring Service Optimization Using AWS

Founded in 1921, State Auto provides insurance in nine lines of business—including auto, home, and commercial—through independent agents and agencies in 33 US states. In early 2020, State Auto began exploring new ways to improve the service experience for its customers and CSRs alike. To rebuild its web application and provide a new data-driven interface for its CSRs, the company used AWS services—including Amazon Connect, which companies can use to set up a contact center in minutes—and rolled out the SA360 project in September 2020. “Using the AWS technology stack, we were able to redesign the user interface for agents to give a more seamless, intuitive interaction,” says Mark Skaggs, IT director of platform engineering at State Auto. “We were also able to establish a better relationship with customers by implementing their feedback in a much shorter time frame."
”State Auto was able to derive insights from millions of calls made to CSRs by using Amazon Transcribe, which uses automatic speech recognition to convert speech to text quickly and accurately. “Transcription is step one for anticipating the needs of customers who call us, and we build on top of it,” says Uthra Ramanujam, vice president of strategic technology research for State Auto. “Because AWS services do their job so well out of the box, we have the flexibility to be creative and build things on top of them.” State Auto built 15 ML models from the data it accrued using Amazon Transcribe. The company uses these models to help CSRs better address calls from customers and to improve its web application so many customers can find what they need online and avoid the hassle of calling for information. These models now accomplish the work that State Auto would have previously needed 8–10 employees to do, assessing 5,000 claims calls per week for call experience, caller, and call reason attributes. Additionally, because the solution was built using AWS Step Functions, a low-code visual workflow service, State Auto can turn on call listening and gain insights using existing models for an entire department in 20 minutes. “Using AWS Step Functions gives us the ultimate flexibility of getting different insights at different points in time depending on the need,” says Ramanujam.
The implementation of State Auto customer service technologies and automation using AWS services has resulted in early efficiency gains and expense reductions. Call reductions and efficiency gains have saved an estimated $800,000 in service operating expenses while also increasing the user experience. After seeing the success of its SA360 initiative, State Auto had the confidence to move forward with building more solutions on AWS for different steps in the insurance life cycle.

Implementing Customer-Focused Workflow Optimization

By using managed services for computer vision from AWS, State Auto has been able to automate processes that it previously performed manually. To simplify the property inspection process, the company uses Amazon Rekognition, which automates image and video analysis with ML and offers pretrained and customizable computer vision capabilities to extract information and insights. State Auto is able to use Amazon Rekognition to tag non-industry-specific risk factors in photos and videos from property inspections, giving risk engineers more time to focus on identifying industry-specific aspects in their risk assessments. To train State Auto’s ML models, the company extensively used Amazon SageMaker Ground Truth, a data labeling service. After the model went live, the company also used Amazon Augmented AI (Amazon A2I)—an ML service that makes it simple to build the workflows required for human review—for active user validation.

State Auto also uses Amazon Textract—which automatically extracts printed text, handwriting, and data from scanned documents—to index documents using a wide variety of business optimization use cases. “Our use of Amazon Textract touches almost every step in the insurance life cycle,” says Ramanujam.

Beyond managed services, State Auto is also using serverless architecture to power its antifraud solution, which combines the expertise of the company’s business users with data-driven insights. The solution was built on AWS Lambda—a serverless, event-driven compute service that lets companies run code for an application or backend service without provisioning or managing servers—and uses AWS Step Functions. The whole solution was seamlessly brought together using AWS Glue—a serverless data integration service that makes it easy to discover, prepare, and combine data for analytics, ML, and application development. After a hassle-free deployment of the fraud detection service, State Auto can now assess 83 percent more total claims for potential fraud than before, identify suspicious claims 3 days earlier in the claims process, and catch the 20 percent of claims that would previously have gone unflagged.

Using AWS to Standardize Operations

Going forward, State Auto is planning to establish internally standardized development guidelines so that its various teams can maximize the benefits of using AWS tools to solve common problems. The company also hopes to combine more of the solutions it is building on AWS in an automated fashion by relying on ML to monitor the process. “The next level of maturity for us would be to see how we can get these capabilities to merge and combine with enough controls in place,” says Ramanujam. “We know the art of the possible, and I think automating all those checks and balances will help us do bigger, greater things.”

Building solutions using AWS resources has increased operational efficiency for State Auto by empowering the company to address its customers’ needs more directly, and the company continues to see the benefits. “Using AWS services has increased our overall agility and flexibility in developing solutions and facilitated a faster, less costly, and better delivery of our capabilities across the board,” says Skaggs.

About State Automobile Mutual Insurance Company

Founded in 1921, regional property casualty insurer State Automobile Mutual Insurance Company provides insurance in nine lines of business, including auto, home, and commercial. Serving 33 US states, it has assets of $4.6 billion and writes $2 billion in premiums.

Benefits of AWS

  • Increased number of claims reviewed for potential fraud by 83%
  • Mitigated an estimated $800,000 in service operating expenses
  • Facilitates detection of fraud 3 days earlier
  • Increased operational efficiency

AWS Services Used

Amazon Rekognition

Amazon Rekognition offers pre-trained and customizable computer vision (CV) capabilities to extract information and insights from your images and videos.

Learn more »

Amazon Textract

Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents. It goes beyond simple optical character recognition (OCR) to identify, understand, and extract data from forms and tables.

Learn more »

Amazon Transcribe

Amazon Transcribe is an automatic speech recognition service that makes it easy to add speech to text capabilities to any application. Transcribe’s features enable you to ingest audio input, produce easy to read and review transcripts, improve accuracy with customization, and filter content to ensure customer privacy.

Learn more »

AWS Step Functions

AWS Step Functions is a low-code, visual workflow service that developers use to build distributed applications, automate IT and business processes, and build data and machine learning pipelines using AWS services. Workflows manage failures, retries, parallelization, service integrations, and observability so developers can focus on higher-value business logic.

Learn more »

Get Started

Companies of all sizes across all industries are transforming their businesses every day using AWS. Contact our experts and start your own AWS Cloud journey today.