AI Use in Fraud Detection to Triple by 2021

While only 13 percent of organizations use artificial intelligence and machine learning to detect and deter fraud, another 25 percent plan to adopt such technologies in the next year or two — a nearly 200 percent increase. Fraud examiners revealed this and other anti-fraud tech trends in a cross-industry, global survey by the Association of Certified Fraud Examiners, developed in collaboration with analytics firm SAS.

The inaugural Anti-Fraud Technology Benchmarking Report examines data provided by more than 1,000 ACFE members about their employer organizations’ use of technology to fight fraud. Other notable trends include:

  • The rise of biometrics. About one in four organizations (26 percent) use biometrics as part of their anti-fraud programs; another 16 percent foresee deploying biometrics by 2021.
  • Increasing budgets. More than half of organizations (55 percent) plan to increase their anti-fraud tech budgets over the next two years.
  • Changing data analysis techniques. By 2021, nearly three-quarters of organizations (72 percent) are projected to use automated monitoring, exception reporting and anomaly detection. Similarly, about half of organizations anticipate employing predictive analytics/modeling (52 percent, up from 30 percent) and data visualization (47 percent, currently 35 percent).

“As criminals find new ways to exploit technology to commit schemes and target victims, anti-fraud professionals must likewise adopt more advanced technologies to stop them,” said Bruce Dorris, president and CEO of the ACFE. “But which technologies are most effective in helping organizations manage rising fraud risks? The answer to this question can be crucial in successfully implementing new anti-fraud technologies.”

“Understanding peers’ technologies and strategies can help organizations determine where the industry is headed and guide their anti-fraud tech investments,” said James Ruotolo, senior director of products and marketing for fraud and security intelligence at SAS. “The dramatic rise of AI, machine learning and predictive modeling reveals that, beyond the hype, advanced analytics is helping investigators keep steps ahead of increasingly sophisticated fraudsters.”

Respondents for the survey hail from 24 industries — banking/financial services is represented most prevalently (21 percent of all respondents_) — and span the globe. So how do the financial industry stack up against the cross-industry global trends?

  • AI and Machine Learning
    • Globally, 19 percent of banks currently use AI and ML for anti-fraud; another 36 percent plan to adopt those techniques in the next two years (55 percent using AI/ML by 2021, a 189 percent increase).
    • Looking exclusively at U.S. banks, one in five (20 percent) currently employ AI and ML to fight fraud, with another 27 percent expecting to adopt (47 percent using AI/ML by 2021, a 135 percent increase).
  • Predictive Analytics/Modeling
    • Globally, one in three (33 percent) banks use predictive analytics/modeling to fight fraud, and 26 percent more anticipate adopting the technology (59 percent using predictive capabilities by 2021, a 79 percent increase).
    • Those in the U.S. are ahead of the adoption curve, with 43 percent currently using predictive analytics/modeling in their fraud-fighting arsenals; an additional 16 percent expect to deploy (59 percent using predictive capabilities by 2021, a 37 percent increase).
  • Fraud Risks
    • 60 percent of U.S. banks and financial institutions use analytics to detect money laundering (vs. 64 percent globally).
    • Likewise, 57 percent of U.S. banks and financial institutions use analytics to detect fraud by customers (vs. 49% globally).

Complementing the benchmarking report, SAS’ has created an online data visualization tool that it believes will allow users to analyze survey data by industry, geographic region and company size. The size of respondents’ employer organizations ranges from less than 100 employees to more than 10,000.

  • Sign Up

  • Categories

  • Archive

Software: Kryptronic eCommerce, Copyright 1999-2020 Kryptronic, Inc. Exec Time: 0.064662 Seconds Memory Usage: 3.799858 Megabytes