top of page

AI Case Study

An Anonymous UK Insurance firm demonstrates that it can better assess the risk of insuring companies by automatically determining relevant UK court cases with deep neural networks

A UK insurance firm wanted to improve its risk assessment of insured companies by automatically reviewing court case listings that might involve their clients. This would help better align risk premiums at the time of renewal or claims. Using EvolutionAI natural language processing they were able to scan court documents and identify relevant companies and cases even if the company name spellings and use were inconsistent and varied.


Financial Services


Project Overview

"Evolution AI has developed technology with a similarly nuanced understanding of context to pick out companies from all the UK court lists. The project was for an insurance firm that wanted to know about its prospective business clients’ court appearances so it could better understand the risks involved in insuring them.

Evolution AI’s system autonomously reads the hourly updates of the publicly available case lists published daily by all UK courts. It identifies every company mentioned in the court lists and links each one to cases and dates."

Reported Results

EvolutionAI claim they generally were able to identify all relevant court cases against companies saving much manual effort for this insurance company. This improved their ability to assess risk when it came to company renewal or claims.






Insurance companies want to better understand the risk associated with insuring companies. Every day there are hundreds of court case lists published in myriad formats and documents. It is an overwhelming task to determine if a company has or is involved in a legal wrangle. It is also challenging for basic search algorithms to determine this information as company names can often be spelt differently. "Companies rarely appear with clear indicators like LTD or PLC but humans can still recognise them using general knowledge and subtle contextual clues, even if the names are misspelled.



UK court case lists.

bottom of page