Fraud

Will Big Data Transform Fraud Detection? | SmartData Collective

The folks over at Smart Data Collective have an interesting story today on Big Data and its (expected) impact on a variety of industries and business practices. Fraud (and fraud detection), it turns out, may be one area that is transformed by better data analytics.

Google-DataCenter
Data analytics is poised to transform the fraud detection industry.

According to the article, by Monte Zweben, fraud analytics are posed to be transformed not just by “Big Data,” but by better and faster analytics.

The article looks at a variety of industries, including consumer marketing and logistics that stand to benefit from the growth in data and data analytics. Fraud detection is one of them.

Zweben cites statistics on the growth of fraud as a global problem. Kroll’s most recent Global Fraud Report found the number of companies falling victim to fraud has increased to 70 per cent.

Credit card companies were among the first to embrace “Big Dat” analytics to spot irregularities in patterns of charges that are indicative of a compromised or stolen credit card. Banks and other financial services firms soon followed suit.

Zweben notes that patterns “typically become stronger with more data points which gives financial services companies, retails and other high-volume players the impetus to look at as much data as possible.”

But fraud detection is exquisitely time sensitive, and scaling analytics is a problem. “When a bank has to process voluminous historical data along with real-time data nightly to detect fraud, it becomes nearly impossible to keep up with both the volume and velocity of data,” he said.

That may be about to change, he argues, as “new real-time Big Data platforms enable companies to process massive quantities of historical information and cross check new transactions in real-time to spot patterns and halt a transaction before it occurs.”

Historically, fraudsters have proven resilient: using structuring (or “smurfing”) to keep their fraudulent activities below the threshold that catches the eye of automated systems. But, with near real-time data on fraud, banks and credit card companies can stay one step ahead of fraudsters: tweaking countermeasures before criminals can adapt to the security measures that are already in place.

Read more via Big Data Use Cases for Traditional Industries | SmartData Collective.

Comments are closed.