FICO, the Silicon Valley based pioneer in the use of predictive analytics and data science to improve operational decisions, this week announced its new Falcon consortium model for payment card fraud detection.
The new model includes machine learning innovations that have been quantifiably proven to cut card-not-present (CNP) fraud losses by 30% without increasing false positive rates, according to the company.
The new models are also able to double the detection of fraudulent, high-value CNP transactions on the first attempted transaction, FICO says.
The models will be released to FICO® Falcon® Platform customers at no additional charge. The FICO Falcon Platform protects more than 2.6 billion payment cards worldwide.
The new models for both credit and debit cards will be available first for FICO® Falcon® Platform customers in the UK and Europe this autumn, and then to customers in other markets worldwide.
More information can be found in a FICO white paper at: http://www.fico.com/en/latest-thinking/white-paper/5-keys-applying-machine-learning-ai-in-enterprise-fraud-detection
CNP fraud, which includes online card and e-wallet transactions, is the most prevalent form of card fraud in most countries. FICO and Euromonitor International found that CNP fraud represented some 70 percent of card fraud in 19 European countries, and rates are similarly high in many other parts of the world.
The Falcon consortium — a pool of anonymised transaction details collected from 9,000 financial institutions worldwide — allows FICO data scientists to test and prove the performance of new models prior to release, the company says.
“Machine learning algorithms are greedy — they gobble up data,” said Dr. Scott Zoldi, FICO’s chief analytics officer. “Fortunately, our unique Falcon consortium has rich, anonymised transaction data on billions of payment cards and merchants, allowing us to build and validate algorithms that represent deep behavioural patterns. In production, these learned highly predictive behavioural variables and profiles of cardholders and merchants are updated with each transaction, in real time, in order to identify and adapt to behavioural outliers.”
FICO has been applying AI-based behavioural analytics for the past 25 years to detect fraudulent transactions across billions of payment transactions. The company today holds more than 90 patents related to artificial intelligence and machine learning in fraud detection.