Automated immediate settlement for small claims with NLP

With the help of a feasibility analysis, showstoppers are identified and recommendations for action are made.

U

Identification of Data points to enable the automatic settlement of minor claims

Reduction of settlement times from several days to just a few minutes

+

Know-How Transfer concerning the application of Machine Learning Methods to clients

Challenge

An international insurance group wants to test whether reported small claims can be settled immediately in an automated manner. Information on the policyholder, contract and damage is available in a structured format. In addition, damage descriptions are available as text. Standardized expert reports are available as PDF documents.

Solution

Modeling approaches are created in close cooperation with the departments. The damage descriptions are processed using modern Natural Language Processing approaches Training of models for classification of damage is done on the basis of the structured data and processed descriptions. Gaps in the data mapping of the regulatory process are identified.

Result

A catalog of 26 data points to be collected has been prepared, which are necessary for the settlement of small claims. Adesign has been created for the onlinereporting process that can be automated. By implementing automation, the regulation time can be reduced from several days to a few minutes in the future.

Are you interested in your own use cases?

Data Science Use Cases

Data & AI Knowledge

Creating joint value from Data & AI

Blog

Discover professional articles about Data & AI and current industry news.

Webinars

Dive into our Best Practices and Industry Exchanges. Discover new dates and recordings of past webinars.

Whitepaper

Learn more about the use of Data & AI in your industry through our white papers, case studies and research.