{"slug":"eazy-asigurari-builds-an-ml-driven-insurance-pricing-engine-on-amazon-sagemaker-ai","url":"https://findausecase.com/use-cases/eazy-asigurari-builds-an-ml-driven-insurance-pricing-engine-on-amazon-sagemaker-ai","title":"Eazy Asigurari Builds an ML-Driven Insurance Pricing Engine on Amazon SageMaker AI","description":"Romanian cloud-native insurer Eazy Asigurari built a proof of concept for a data-driven pricing engine using Amazon SageMaker AI, AWS Glue, Amazon API Gateway, Amazon RDS for PostgreSQL and Amazon DynamoDB. The ML models backtest premiums and highlight potential deviations across thousands of customer segments, with the actuarial team reviewing all ML outputs before informing pricing decisions. The proof of concept was completed within 2 months and the insurer reduced data analysis time by up to 80 percent.","company":"Eazy Asigurari","industry":"Insurance","country":"Romania","aiCapabilities":["Predictive Analytics"],"technology":["AWS Glue","Amazon API Gateway","Amazon RDS for PostgreSQL","Amazon DynamoDB","Amazon SageMaker AI"],"deployment":"Unknown","problemStatement":"Romania's insurance market is highly regulated, limiting flexibility in how insurers calculate premiums, while customers can compare prices online with minimal effort and even small price differences can prompt them to switch providers, particularly for mandatory products such as motor third-party liability.","solutionApproach":"Rather than replacing its existing pricing framework, Eazy Asigurari is enhancing it with ML capabilities on AWS. AWS Glue handles data ingestion and transformation, Amazon API Gateway secures data intake workflows, Amazon RDS for PostgreSQL stores the data, and Amazon DynamoDB captures logs and model outputs to support traceability. At the core, Amazon SageMaker AI lets the team build, train and deploy ML models; Eazy Asigurari customized models that can backtest premiums and highlight potential deviations across thousands of customer segments, and its actuarial team reviews all ML outputs before informing pricing decisions.","businessValue":"Eazy Asigurari completed its proof of concept within 2 months and is moving the solution into production. Using the new ML-driven workflow, it reduced data analysis time by up to 80 percent, accelerating decision-making and allowing the company to test scenarios and benchmark results more consistently.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/solutions/case-studies/eazy-asigurari-case-study/","dates":{"publishedAt":"2026-10-12T05:49:54.116Z","publishedAtSource":"pipeline","updatedAt":"2026-10-12T05:49:54.116Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/eazy-asigurari-builds-an-ml-driven-insurance-pricing-engine-on-amazon-sagemaker-ai. Bulk republication requires permission."}