Online sports bookmaker Betfair has seen a growth in activity and click-rate on its website, and a growth in revenue overall due to its use of real-time decision making software behind its website.
The firm made the decision to look into new technologies to personalise the content served on its website, to get away from the ‘one size fits all' approach it had used previously.
James Knight, web capabilities product manager at Betfair, told delegates yesterday at Gartner's Business Intelligence Summit that an initial 23 potential suppliers was eventually cut down to one.
"We went through a rigorous selection process and found 23 potential suppliers. We cut this to a shortlist of six, who performed technology presentations for us, after which we cut to three suppliers."
After visiting firms around the US and Europe, Betfair eventually decided to select Oracle's RTD database.
Knight explained that a key requirement was that the system would be able to learn.
"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."
This is a function that previously required manual intervention, but now happens automatically.
Knight said that an important factor was that this did not slow down the customer experience.
"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."
Knight explained that the system takes data from many different sources in order to decide what content to show to users, based on their demographics and likely areas of interest.
"300 elements of customer data gets 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.
As opposed to the real-time data component, this analysis can happen over a longer period, and does not necessarily involve decision making during the customer's visit.
This has resulted in improved user activity from the parts of the site driven by RTD, which translates to improved revenue.
"We've seen a 400 per cent uplift in click rate in the target group which is driven by RTD," explained Knight.
By eliminating high entry costs for big data analysis, you can convert more raw data into valuable business insight.
A discussion of the "risk perception gap", its implications and how it can be closed