U.S. Markets close in 5 hrs 31 mins

To Catch a Thief: Banks Try Using Big Data

Christina Medici Scolaro
Big Data Download
To Catch a Thief: Banks Try Using Big Data

One of the biggest concerns facing banks and customers has always been identity theft and fraud. As banks come up with new technologies to combat fraud, criminals are nipping at their heels with sophisticated technologies trying to override the banks’ efforts.

One of America’s largest banks, Wells Fargo, is in the very early stages of creating a big data lab that it hopes will allow analysts to prevent and identify fraud. The lab will analyze financial interactions between people and detect if funds are changing hands in unusual patterns that deviate from customers’ established patterns. Wells Fargo said finding these patterns was difficult to do without the right technology, or too difficult to correlate when information was handled through separate data streams.

RELATED: How to Protect Your Smartphone Against Hackers

According to the Bank Systems and Technology website, loans and mortgage companies have started leveraging big data programs to detect external fraud by mining social networks for suspicion of fraud. For example, a person who has been defaulting on his or her loans because of a lack of funds, but who keeps posting images of new purchases (car, consumer durables) on his social media profiles, can be brought within the purview of scrutiny.

Time is of the essence when it comes to identity theft and fraud. Things that would have taken months or weeks to analyze in the past, now takes only hours or days thanks to big data technologies.

RELATED: How Health Care is Mining, Using Your Data

Jim Smith, executive vice president and head of both the digital channels group and enterprise data group at Wells Fargo, said to “Big Data Download”: “We always looked at fraud in lots of different ways, by channel views, by product views but it’s always been a little struggle until we had some of the tools that came available with big data, to look at that data holistically across all those different data sets so we can actually bring that data in to some of the big data environments, analyze the data and react in “near real-time”.

-- Comments, Questions, Suggestions? Tweet Us @BigDataDownload