Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Next generation´s insurance company

Reference number
Coordinator Hedvig AB
Funding from Vinnova SEK 300 000
Project duration December 2017 - July 2018
Status Completed
Venture Innovative Startups

Purpose and goal

The overall aim for the project has been to create an automated (AI-based) system for insurance claims management. During the project three distinct areas have been identified as critical in achieving this goal and has been the focus for delivery: 1) Dynamic pricing of insurance risk 2) Named entity recognition for the Swedish lanague 3) Automatic FAQ for the home insurance domain

Expected results and effects

The project has led to a number of analytical models which has been implemented in Hedvig’s cloud based insurance system. Data structures and infrastructure has been developed in order to continuously update the statistical models as well as the datasets used to train and evaluate them. The project has also led to an increased focus on R&D within and outside the company resulting in a number of collaborations

Planned approach and implementation

The project started out with an analysis phase including a market overview of existing solutions and research activities in the area. This resulted in the selection of three key areas which has been the focus for the remaining project. Each subproject started out with a data collection phase where existing benchmark datasets was identified, and new ones created to cater to our specific insurance domain. During implementation the respective project evaluated a number of hypothesis regarding suitable models. Finally the commercial potential in the solutions was evaluated

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 13 November 2020

Reference number 2017-03931

Page statistics