INSIS AI Life Underwriter

INSIS Machine Learning Framework: handles the entire core insurance model logistics autonomously. The ML pipeline is designed for scalable, high-performance core insurance machine learning tasks. Allows the automation of machine learning models and algorithms to optimize core insurance business processes.

Machine Learning Framework Implementation: quantified ML implementation with ML Test Score to be measured and improved during implementation and over production time. To

Proprietary Framework: raw format data can be stored to be subsequently used for training models; multitenancy; allows models to be built automatically; input and output data can be shared to independent applications (consumers) on premises or in the cloud; performance can be evaluated and monitored; models can be compared with a baseline; models can be deployed with ongoing validation of performance; stage models into the production system for testing without disturbing system operation; can handle hot hand-offs to allow seamless integration of new models in production; automated fallback; better model management guaranteeing that the models are functioning in their allocated document environment.

Model management framework: provides implementation, focused on generating value from Big data without high IT investment.