Featurespace files two global patents for its fraud prevention technology
Featurespace has filed two global patents for its fraud prevention and anti-money laundering technology.
The Cambridge Science Park company says the patents will aid its capacity to help “progressive financial institutions” protect consumers.
The first patent is for Featurespace’s Automated Deep Behavioral Networks for the card and payments industry. A deep neural network architecture of connections and updates, these recognise and prevent fraud cases progressing.
Deep neural networks have been used in areas such as image recognition and text understanding by creating connections and weights that extract meaning from underlying data.
Dave Excell, founder of Featurespace, said: “Financial institutions around the world are experiencing fraud and account takeover at unprecedented levels, with some reports estimating this number at more than $40 billion last year.
“The Automated Deep Behavioral Networks patent and associated technologies deliver the right levels of model performance the industry needs to decrease fraud and protect consumer accounts before attacks happen.”
Featurespaces’s technology solves the challenge of finding a neural net architecture that extracts meaning from transaction sequences, producing a much higher distinction between genuine and fraudulent transactions - meaning it avoids the problem of ‘false positives’, in which consumers are stopped unnecessarily.
The second patent is for Behavioral Anomaly Score, technology that identifies anomalies in individual customer behaviour without any prior knowledge of contextual high-risk behavior. It amplifies the ability to identify when a person’s behaviour is out of character, without any labelled data.
Companies and financial institutions using a Behavioral Anomaly Score can see the exact point at which a person’s behaviour has changed with greater precision.
That means they can construct more complex models for change detection, further reducing incidences of financial crime.
Dave said: “The fight against fraudsters and the organisations that commit financial crime on a large scale is challenging and ever-evolving.
“Technology, specifically machine learning, will continue to be central in this fight and these two patents from Featurespace advance our leading market position and our capacity to help progressive financial institutions protect the consumer.”
A UK Citizens Advice report indicated that one in three adults in the UK were targeted by a pandemic-related scam last year.
And a study by Javelin Strategy & Research reported that identity fraud cost US citizens a total of $56 billion last year, with about 49 million consumers falling victim.
Featurespace filed full public patent applications in the US, UK, EU and Patent Cooperation Treaty (PCT).
Read more
Nine 2021 Queen’s Awards for companies across Cambridgeshire
Cambridge fraud prevention specialist Featurespace raises £30m to continue international expansion
Sign up for our weekly newsletter and stay up to date with Cambridge business
