# FICO Machine Learning Algorithms Improve Card-Not-Present Fraud Detection by 30% Author: Pal Sinha, Barnali Author URL: https://financedigest.com/author/pal-sinha-barnali Published: 2017-10-11 Category: NEWS Category URL: https://financedigest.com/category/news Meta Title: Global Banks Benefit from New FICO Fraud Detection Models Meta Description: Find out how FICO's latest innovations can help global banks reduce CNP fraud losses by 30% without increasing false positives. Protect your customers URL: https://financedigest.com/fico-machine-learning-algorithms-improve-card-not-present-fraud-detection-by-30html ![undefined](https://prod.superblogcdn.com/site_cuid_cm5qst7v3003gwirgwqtxn8i8/images/fd111017-14-1736843401096-compressed.jpg) **_Thousands of global banks to benefit from machine learning that more accurately detects fraud in online and mobile purchases_** **Highlights:** - FICO is releasing new payment card fraud detection models focused on making **card-not-present (CNP) transactions more convenient and secure.** - CNP fraud is the **[leading form of card](https://www.financedigest.com/virtual-cards-will-help-lead-the-travel-industry-into-a-post-pandemic-boom.html "Virtual cards will help lead the travel industry into a post-pandemic boom") fraud** in most countries. - Based on analysis of more than **4 billion transactions**, the new models can significantly [reduce CNP fraud](https://www.financedigest.com/the-importance-of-a-proactive-and-collaborative-approach-to-reducing-contactless-fraud.html "THE IMPORTANCE OF A PROACTIVE AND COLLABORATIVE APPROACH TO REDUCING CONTACTLESS FRAUD") losses without increasing false positive rates. - The new models have been quantifiably proven to double the detection **of fraudulent, high-value CNP transactions** on the first attempted transaction. - The models will be released to FICO® Falcon® Platform customers **at no** [additional charge. The FICO Falcon Platform protects](https://www.financedigest.com/antimicrobial-protection-additives-for-adhesives-market-incredible-possibilities-growth-analysis-and-forecast-to-2028.html "Antimicrobial Protection Additives for Adhesives Market Incredible Possibilities, Growth Analysis And Forecast To 2028") more than 2.6 billion payment cards worldwide. Silicon Valley analytic software firm FICOtoday announced that its new Falcon consortium models for payment card fraud detection include [machine learning](https://www.financedigest.com/machine-learning-engineer-jobs.html "Machine learning engineer jobs") innovations that improve **card-not-present (CNP) fraud** detection by 30% without increasing the false positive rate, a standard metric for fraud model performance. These new Falcon consortium models for both [credit and debit cards will be available first for FICO® Falcon® Platform customers in the UK and Europe](https://www.financedigest.com/credit-agricole-and-caceis-to-buy-rbc-investor-services-europe-unit.html "Credit Agricole and CACEIS to buy RBC Investor Services’ Europe unit") this autumn, and then to customers in other markets worldwide. 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. “Consumer convenience is [driving rapid](https://www.financedigest.com/n95-masks-market-rapid-expansion-of-the-life-science-industry-is-anticipated-to-drive-the-global-market.html "N95 Masks Market: Rapid Expansion of the Life Science Industry is Anticipated to Drive the Global Market") growth in online transactions. As a result, criminals are looking to use this convenience to their advantage as chip cards and other security features have made physical card fraud more difficult,” said **TJ Horan, vice president for fraud solutions at FICO**. “Our goal is to help card issuers promote a positive consumer experience while protecting them from financial harm. These CNP machine learning innovations are important tools to help issuers spot fraud faster, and take on even greater importance in the [light of recent](https://www.financedigest.com/u-s-lighting-products-market-recent-strategies-trends-technology-innovation-analysis-application-by-tmr.html "U.S. Lighting Products Market: Recent Strategies, Trends, Technology Innovation, Analysis Application by TMR") data breaches, which will lead to more fraud attempts.” The Falcon consortium — a pool of anonymised transaction details collected from 9,000 financial institutions worldwide — allows FICO [data](https://www.financedigest.com/how-to-drive-a-data-culture-in-the-finance-industry.html "How to drive a data culture in the finance industry") scientists to test and prove the performance of new models prior to release. [Developed based on analysis](https://www.financedigest.com/automotive-mems-sensor-market-key-manufacturers-development-trends-and-competitive-analysis-2028.html "Automotive MEMS Sensor Market Key Manufacturers, Development Trends and Competitive Analysis 2028") of 4 billion transactions, these new CNP machine learning models have demonstrated the ability to: - [Cut CNP fraud losses by 30% without increasing false positive rates](https://www.financedigest.com/czech-central-bank-vice-gov-unlikely-to-vote-for-rate-cut-newspaper.html "Czech central bank vice-gov unlikely to vote for rate cut -newspaper"). - **Reduce CNP transaction review** [rates without increasing fraud risk](https://www.financedigest.com/hungary-ramps-up-rate-hikes-as-war-stokes-inflation-risks.html "Hungary ramps up rate hikes as war stokes inflation risks"). - Double the detection of fraudulent, **high-value CNP transactions** on the first attempted transaction. “Machine learning algorithms are greedy — they gobble up data,” said **Dr. Scott Zoldi, FICO’s** [chief analytics officer](https://www.financedigest.com/future-market-insights-appoints-aditi-basu-as-chief-marketing-officer.html "Future Market Insights Appoints Aditi Basu as Chief Marketing Officer"). “Fortunately, our unique Falcon consortium has rich, anonymised transaction data on billions of [payment cards and merchants](https://www.financedigest.com/embedded-payments-for-b2b-merchants-and-marketplaces-4-considerations.html "Embedded payments for B2B merchants and marketplaces: 4 considerations"), 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.” For 25 years, FICO has applied [**AI-based behavioural analytics**](http://www.fico.com/en/analytics/advancing-artificial-intelligence-and-machine-learning) to detect fraudulent transactions across billions of payment transactions, with sub-second response times. The FICO® Falcon® [Platform protects](https://www.financedigest.com/digital-id-revolutionises-end-to-end-mortgage-and-protection-platform.html "Digital ID Revolutionises End-to End Mortgage and Protection Platform") more than 2.6 billion payment cards worldwide. The company today holds more than 90 patents related to [artificial intelligence and machine learning](https://www.financedigest.com/machine-learning-in-artificial-intelligence.html "Machine learning in artificial intelligence") in fraud detection. --- This blog is powered by Superblog. Visit https://superblog.ai to know more. ---