AI-based Application Control for SV

AI-based Application Control for SV
File:SV SparkassenVersicherung logo.svg - Wikimedia Commons

This case study gives an overview on the AI-based product (or the machine learning application if you prefer) that we built for the insurance SparkassenVersicherung (SV) to accelerate its “Complex Biometric Risk Assessment Process”.

Key Challenges

Our client offers disability insurance (for people who are no longer able to work) and term life insurance. They receive many applications via detailed questionnaires filled out by applicants.

The initial process was time consuming and some of the applications were not conform (and therefore required special attention).

Our client was looking to:

Our Approach

To meet our client’s expectations, we took the time to understand the current application process and data processed in order to propose the best data-driven and automated solution to implement.

We therefore built an interdisciplinary team with members from risk assessment department, IT and data lab. Together we agreed to automate the process via a machine learning model capable of performing complex automations based on the assessment of biometric risks (information that was received in the applications).

We increased the maturity in a cyclic and agile way from a first conception, via a successful piloting phase to a final deployment and integration of the process into the existing architecture and processes via web services. The development of the models was carefully done, for example by performing regular human checks on random samples, so that the final process can pass the compliance audits that insurance companies are subject to.

Replay on-demand webinar AI Strategy Webinar with DAT
Replay on-demand webinar AI Strategy Webinar with DAT

Benefits

Technologies & Partners

Team involved

A Project Manager & a Data Scientist collaborated with the insurance expert for 18 months to build this AI-based Application.

Discover our Data & Analytics services

Newsletter subscription