Behavioural analytics technology tells if it fraud or not

shutterstock_157028693As the advances of technology within the retail space make purchasing ever easier for the consumer, they too open the door to potential fraudulent activity. With this in mind, retailers, banks and creditors will be pleased to know that there is a solution to this fear by way of machine learning analytics that can both protect and understand the shopping nature of every consumer.

Callcredit, the second largest credit reference bureau in the UK and an expert in managing consumer data for retail businesses, has invested in machine learning analytics to improve its fraud detection offering. The company paired with Featurespace which will provide advanced learning behaviour analytics to analyse its large amounts of data. Featurespace claims to be developing algorithms that will enable them to understand peoples’ behaviours in real time, and calculate their next spending steps. On a reassuring and also a little scary note, the company may actually have information about nearly everyone in the UK.

The aim is to use Featurespace’s Adaptive Behavioural Analytics (ARIC) engine to spot fraud as it happens by learning of trends and patterns happening within Callcredit’s consumer data. The intuitive technology literally learns as it goes along and in doing so it begins to understand spending habits, picks out possible fraudulent triggers or actions, and determines for itself whether it is actually fraud or just a change in spending behaviour taking place.

John Cannon, Callcredit’s head of fraud & ID commented, “We have lots and lots of data, which is great, but having analytics to spot the value of the data is just as important. Equally important is spotting behavioural changes that might look unusual and may be fraud, but are just changes around the individual that is actually not fraud.”

He explains, “Let’s say a credit or debit card gets declined by the bank for unusual behaviour – for instance when you’ve gone abroad – it’s an inconvenience for the customers and not a great experience,” he says. “That behaviour is different, but there’s a reason, so the system can allow genuine customers to get through.”

To summarise, the set up works like so, Featurespace provides both a synchronous and asynchronous event based application programming interface, which enables Callcredit to alert Featurespace of events within their platform aka consumers or fraudsters spending or accessing money. These events are processed and analysed by the software which then works out the chance of fraudulent activity taking place. In keeping with the demands of flexible technology, the software is available as either an on-premises or cloud-based solution and can be modified to suit specific requirements.

Source – http://www.computerweekly.com/news/2240204046/Callcredit-invests-in-machine-learning-analytics-to-improve-fraud-detection