Pro-actively question your data using AI and data analytics

Cognitive Analytics (a combination of AI and data analytics) allows GRAPHT to draw eyes to previously unseen and relevant information either by clustering relevant items together or by extracting data out of hard-to-reach places.

“GRAPHT is not just displaying data, it’s discovering structure, meaning, and relationships that don’t yet formally exist.”

Clustering

GRAPHT can cluster items together by text, space or time. For example it could identify:

Claims that occur within 200m of each other in time and space
Policies that have a similar address or postcode
Clusters of claims submitted minutes apart from the same IP region

GRAPHT can manifest new networks based around this newly identified information to give new insights into a dataset.

This means that GRAPHT is not just displaying data, it’s discovering structure, meaning, and relationships that don’t yet formally exist in the data model.

Extracting data out of hard to reach places

Sometimes the richest fraud clues live in unstructured text, the “version of events,” claim narratives, repair notes or witness statements. GRAPHT uses AI to tap into this data, unlocking it’s potential.

By extracting the data points (people, organisations, locations) from this data, GRAPHT allows it to be analysed alongside the existing structured data points.

Suddenly unstructured narrative becomes structured evidence. It’s not just a visualisation platform, it’s an active discovery engine for organised fraud.

Introducing GRAPHT

It’s estimated that undetected fraud costs a large UK insurer between 100 - 120 million a year.¹

Can your organisation afford to not use GRAPHT?

Detected insurance fraud in the UK was estimated at £1.1 billion in 2022 (ABI). Studies suggest a similar amount of fraud goes undetected each year, implying total UK fraud of roughly £2.2 billion. Large insurers with 10% of the UK market would therefore face a total fraud exposure of £220 million annually, of which approximately half (£100–120 million) is detected, with a similar amount (£100–120 million) estimated to be undetected.