Machine learning is crucial for fraud management


Data image-DARPA-Greg machine learning blogLately there seems to be a surge in the term machine learning. Much like big data a few years ago, machine learning is the new buzzword -- and the two terms actually go hand in hand.

With increasing volumes of data now stored in distributed environments such as Hadoop, it's possible to quickly produce models that can analyze bigger, more complex data, and deliver faster and more accurate results – two critical elements in the battle against fraud.

The more time it takes to discover an instance of fraud, the more the victim organization loses. Association of Certified Fraud Examiners (ACFE) estimates fraud costs organizations 5 percent of annual revenues worldwide. Applying machine learning techniques to large, complex data sets allows fraud management solutions to offer these needed results faster.

So what are some of the benefits of machine learning in fraud management?

  1. The ability to identify rare events and non-obvious fraud in large volumes of data.
  2. The capacity to handle data with multiple features (tens of thousands) to identify variables that are predictive of behavior.
  3. Using both unstructured data and structured data in one model. This is useful, for example, in the case of extracting names, addresses and phone numbers from call logs to use for investigation.
  4. The ability to automatically adapt to changing patterns within the data. In fraud, accuracy equals dollars saved, so better predictions are of utmost importance.
  5. The opportunity to simultaneously apply a variety of machine learning methods to identify patterns that may have previously gone undetected. Where one method fails, another may prevail.
  6. And finally, the ability to run analytics in real time to identify fraud as it is happening to prevent losses, rather than merely identifying them after the fact.

SAS has been integrating machine learning techniques into our analytics platform for decades, including our fraud solutions. One of the key differentiators among vendors in The Forrester Wave™: Enterprise Fraud Management, Q1 2016 was machine learning. The report gave SAS among the highest scores in the current offerings category, with the highest scores among all vendors in the strategy and market presence categories.

Be sure to take a look at the full Forrester Wave™: Enterprise Fraud Management, Q1 2016 report on our website.


About Author

Greg Henderson

Government Solutions Architect

Greg Henderson is a Government Solutions Architect in the Fraud and Financial Crimes Global Practice at SAS. In his current role, Greg is in charge of field support and product direction in applying SAS’ fraud detection and prevention capabilities within the government market. During his 13 years at SAS, Greg has worked in various sales, marketing and technical roles applying SAS’s data integration and analytical capabilities to solve real-world business problems. He led the development of SAS’ market leading anti-money laundering solution, and for the past 6 years has focused exclusively on applying his knowledge and skills in the government space. He has authored several papers and presented at industry events on these topics. Greg holds a degree from Bowling Green State University, and resides in Raleigh, NC.

Comments are closed.

Back to Top