William Hill uses machine learning to fight off 'constant' cyber attacks

'A machine can learn what's normal and can spot anomalies more easily than a thousand people,' CTO Finbarr Joy tells Computing

Bookmaker William Hill is deploying machine learning techniques to help protect its services and its customers from "constant" cyber attacks and other threats from hackers.

That's according to Finbarr Joy, chief technology officer at William Hill, who told Computing that the use of machine learning and other advanced algorithmic techniques can much more quickly spot the abnormal behaviour associated with intrusions than a human can.

"It's constant," Joy said when asked about cyber attacks, "which means we're using a lot of technology to stop those patterns of behaviour. How do you spot a pattern that's different from the normal?"

The most useful method for doing that, he argued, is by deploying machine learning algorithms

"It builds up a graph of normal activity and builds that up over time," Joy explained, describing how, by using this technique, William Hill is able to streamline its response to cyber security incidents and also detect things that people could never spot.

"When things are happening outside of the normal patterns, it makes those explicit then you can zero in on them. It's a good example of how a machine can learn what's normal and therefore can spot anomalies much more easily than a thousand people," said Joy.

With machine learning being such an important aspect of William Hill's cyber defences, Joy explained that the company's security team consists of "software engineers more than anything else" who spend their time "looking at ways of automating and finding patterns of disruption".

"It's not about classic barrier security, it's about interacting and working with scenarios and we're certainly using machine learning in that capability as well, that's one of the heavily used aspects of it, spotting patterns of customer behaviour," he told Computing, explaining that cyber security is one of the most important aspects of William Hill's wider technological transformation.

"One of the most significant elements of our journey is how security is managed as we go through this," Joy said. "[Our security] team is a very digital team and an engineering team."

While many businesses are just taking their first steps into harnessing machine learning, Norbert Wirth, global head of data and science at global marketing and research firm GfK, recently told Computing that in the future, machines, not people, will make marketing decisions.

While humans will continue to have a very important role in making marketing decisions, it will "be absolutely not feasible" for them to make them as quickly and efficiently as machine learning algorithms can, he said.

Computing's full interview with William Hill CTO Finbarr Joy will be published in the very near future.