Machine Learning-based models to quantify commercial fleet exposure at individual insured asset risk in real-time
Learn how Humn.ai moved to a Kubernetes-based, Apache Flink® infrastructure within weeks
Explore the architecture of the Humn.ai Machine Learning-based platform for dynamic risk assessment.
Discover how Humn.ai upgraded Apache Flink® jobs to production with Ververica Platform
"When we migrated to Kubernetes with Ververica Platform it was much easier for our developers to define and configure jobs, as well as manage and monitor them in an integrated and efficient manner."
Co-founder and CTO, Humn.ai
Humn.ai uses Ververica Platform and Apache Flink to build a Machine Learning-based platform producing dynamic risk assessment models and real-time pricing for tomorrow’s insurance industry.
Humn.ai deployed Ververica Platform with Apache Flink to harden production Flink jobs seamlessly and quickly.
They developed a Machine Learning-based platform that is Kubernetes-native and implements ML-based algorithms for calculating the risk of vehicles in real-time. The risk scores for each insured asset is calculated dynamically and then updates a premium variable part of the insurance policy in real-time.
This case study includes:
The challenges Humn.ai faced with their previous technology stack and how Apache Flink helped in resolving them
The results achieved by deploying Ververica Platform and Apache Flink to production
A detailed overview of Humn.ai's experience using Ververica Platform