Betfair web chief James Knight told delegates at the Gartner Business Intelligence Summit that the system is able to automate tasks that previously had to be performed by staff.
Before the system – Oracle’s RTD database – was in place, content editors would have to watch matches and other sporting events, physically entering data such as scorelines into the system as they occurred.
He explained: “We wanted a self-learning system. The system has to know how to categorise people. For example, once it has seen that the majority of people of a certain age from a certain country like betting on a certain sport, it will start suggesting that.”
“On average we are making 2,500 decisions per customer in around 50 miliseconds. Decisions like which sport we should drive the customer to. That means we can use this on the web, and serve it to mobile devices.
“More than 300 elements of customer data get pushed into Oracle RTD, such as behavioural data, what they are doing on site, what information they look at, and we have information coming from the sporting and betting market every minute.
“The system takes this info and pushes out relevant content to customers. Feedback then goes to RTD so it can learn if it has been successful.”
The firm then uses web analytics to understand the impact it is having on the user journey. It is able now to find out if the personalised content is taking customers away from areas they are more interested in, and thus more likely to bet on, or instead if it is encouraging them to bet more.
“We have seen a 400% uplift in revenue from the control group,” explained Knight.
To leave a comment please register – it takes less than a minute and is free of charge. You will also get our weekly email update The DM Report (to opt out contact firstname.lastname@example.org). If you are an existing user, please log in. If you have forgotten your log-in details please email email@example.com to get them reset!