tetrel Logo tetrel Logo

Whitenote: Identifying cyber risks in commercial contracts

2021-10-13 by Johannes Humbert (LinkedIn | Twitter)

Identifying explicit and implicit inclusions of cyber risks in commercial insurance contracts in wholesale individual business is an eminent part of the value chain. And NLP is the solution.

Bridging the Gap

While in the insurance industry some of the high volume of documents directly contain structured data for further processing, for example forms, this is not always the case with contracts, they do not follow a predefined pattern, they cannot be easily processed automatically. But it is precisely in these sources that a lot of valuable information is hidden.


  • Cyber is explicitly and implicitly included in insurance contracts.
  • These contracts are not standardised and therefore cannot usually be documented in a structured way.
  • There is no clarity about the overall cyber risk in the portfolio.


  • The wording in contracts is heterogeneous.
  • The contract portfolio is inconsistent due to indexation and different tariff generations.
  • Underwriters are too valuable a resource to be tasked with a manual evaluation.
  • Traditionally, large amounts of data are needed to train an NLP model.


  • Identify typical phrases using a few sample documents.
  • Training of an NLP model with corresponding synthetically generated training data.
  • Evaluation of the inventory with the trained model.

Extract unstructured information from contracts and claims notices using Natural Language Processing (NLP).

Read the full whitepaper Bridging the Gap - More productivity and lower costs through automation of knowledge-based processes here.

Your contact

Johannes Humbert
+49 176 83 33 51 46