Home   Business   Article

Battling fraud with more Featurespace


By Paul Brackley | Feb 3, 2017


Featurespace, The Hauser Forum, 21 JJ Thomson Ave, Cambridge, from left Tim Kelby Technical Communicator, Lucy Griffin Data Scientist, Simon Rodgers Director of Engineering, Karthik Tadinada Director of Data Science . Picture: Keith Heppell
Featurespace, The Hauser Forum, 21 JJ Thomson Ave, Cambridge, from left Tim Kelby Technical Communicator, Lucy Griffin Data Scientist, Simon Rodgers Director of Engineering, Karthik Tadinada Director of Data Science . Picture: Keith Heppell

Featurespace is going up in the world – and not just because it’s moved up a floor at its Cambridge headquarters.

Martina King, CEO, Featurespace
Martina King, CEO, Featurespace

The company, which uses machine learning to predict and prevent fraud, is taking on more staff as its unique technology drives international growth.

CEO Martina King told the Cambridge Independent: “It’s great, homegrown Cambridge technology that is now really beginning to capture the imagination of the fraud prevention world and as a result it has terrific commercial traction.”

Featurespace was founded out of the Cambridge Engineering Department in 2008 by Prof Bill Fitzgerald and Dave Excell. Their pioneering research created the world’s first Adaptive Behavioural Analytics engine, the ARIC platform.

“What we have is a unique and different understanding of how humans behave from the dataset we observe. We monitor all events that take place in the data and predict what will happen next. We anomaly detect to see if there’s a change occurring and then create an alert.

“Most existing fraud systems out there have to understand what known fraud looks like and then they build a model off what a known attack is and protect consumers. Our methodology enables organisations to be protected from previously unseen or unknown attacks because we are protecting each consumer at an individual level.”

It is technology that has been looking out for unusual betting patterns for BetFair – the firm’s first client – since 2008 and has grown to protect financial services companies, including retail banks, payment providers and card issuers.

Martina added: “We have been able to make great progess in the gaming sector and our single largest market is financial services. The insurance market is also an interesting one for us.”

Customers include Camelot, William Hill, Vocalink/Zapp and TSYS, the largest third-party processor of Visa and MasterCard credit cards in the US. Further international expansion is expected.

“We’ve got off to a flying start in 2017,” said Martina.

So how is Featurespace beating off other fraud prevention systems to land new contracts?

“The beauty of our system is our models never degrade,” she explained. “Once the system goes in and models are up and running, they do not deteriorate. That’s a pretty unique thing – that’s the self-learning part. A new type of fraud attack is identified, the model is taught that and then it can identify that fraud attack from there on in. The best predictor of tomorrow’s fraud is yesterday and there’s no system in the world that can update in real time.”

Featurespace’s international headquarters in Cambridge have shifted up to the third floor of the Broers Building on the Hauser Forum to accommodate new staff and add capacity for further growth. Engineers and scientists work in Cambridge, while its London offices, which feature the commercial team, have moved to Bishopsgate in the City of London.

Seven new members have been added to the commercial team – including two subject matter experts in financial services and gaming – while four have been added to the engineering and data science team. The firm employs 73 in total and has now deployed ARIC to organisations with services or products deployed in more than 180 countries.

Martina added: “It is a very exciting time here at Featurespace.

“We are proud to continue to invest in Cambridge.”



COMMENTS
()


Iliffe Media does not moderate comments. Please click here for our house rules.

People who post abusive comments about other users or those featured in articles will be banned.

Thank you. Your comment has been received and will appear on the site shortly.

 

Terms of Comments

We do not actively moderate, monitor or edit contributions to the reader comments but we may intervene and take such action as we think necessary, please click here for our house rules.

If you have any concerns over the contents on our site, please either register those concerns using the report abuse button, contact us here.

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies - Learn More