Filtering the Fraudster: Building a Picture Using Big Data
In our new Insight Paper, we focus on how merchants can build an effective fraud filter for their sales funnel – one that is not over-restrictive, leads to genuine sales being accepted, and prevents genuine fraud. Get the balance right and merchants stand to improve their checkout conversion rates and boost their bottom line.
But the right balance – and being able to build an effective fraud filter – requires merchants to first see fraud to understand what their fraud looks like, and to recognize how fraud differs from genuine transactions.
Start with data
Through using a wealth of data—based on thousands upon thousands of transactions—merchants can build a picture of both fraudster and customer behavior, which helps to establish the context for fraud management.
The best data solutions dig deep into every transaction, gathering intelligence from every conceivable data point. Payment providers and merchants need systems capable of capturing and collating these massive amounts of data, so that it can be analyzed for trends, even as those trends are still emerging or evolving.
The data that one merchant gathers can be used to sketch out patterns within their customer base, but is also critical to building rich intelligence and a good understanding of emerging fraud trends within – and across – market segments and geographies. This can only be achieved through constantly updating fraud management systems with information from both internal and external sources, including hot card files, chargeback data and information traded on the dark web.
Fraud exchange services can also play a valuable role here — connecting merchants and issuers in a multi-directional information exchange, which boosts the ability of all parties to make accurate and informed decisions.
The richer and more intelligent data becomes, the more accurate, effective and efficient fraud detection strategies become. This in turn reduces the impact on genuine customers and checkout conversion rates.
Leveraging data with machine learning
Machine learning applies pattern recognition techniques to transaction data, from both fraudulent and genuine transactions, to build algorithms that can predict the probability of a transaction being fraudulent. These predictive models, with their ability to extract meaning from complicated data, can identify patterns too complex for humans or automated techniques to flag.
Machine learning, and its ability to crunch huge data sets, is complementing more traditional fraud indicator tools. And when machine learning models are correctly ‘trained’ (using mass amounts of relevant transaction data) and configured correctly by experts, these techniques can be used to block fraud behind the scenes, invisible to shoppers, with no harm to conversion rates.
By more accurately pinpointing fraud, machine learning models also help to support better conversion rates, by reducing false positives and ensuring genuine customers do not get unnecessarily declined or delayed by manual review processes.
Because machine learning models learn from experience, they can struggle to spot monolithic events, and can underperform when customer buying patterns suddenly move away from the norm. It is therefore important that machine learning forms just one part of an overall fraud management solution, just as expert human analysts remain critical to interpreting and acting upon the wealth of transaction data now available.
For more advice on managing fraud and sales performance, download our new insight paper, ‘Driving Up Conversion with Effective Fraud Management.’
Related Blog Posts
Women in Payments: It’s Time to Get Out of Your Comfort Zone
As we gear up for Money 20/20 U.S next month, we are excited to shine a spotlight on Natalia Ruiz, manager, Payments Risk Solutions at ACI Worldwide, who was recently selected to be part of the 2019 Rise Up Academy. This global program created by Money 20/20 addresses the gender imbalance in leadership positions within the Financial Services and Fintech industry.
Universal Confirmations: Get Ready for 2020
With the arrival of universal confirmations, we sit down with some industry experts to find out more about what impact this will have on transforming cross-border payments. We’re welcomed by Fabien Depasse - Head of SWIFT gpi Customer Success at SWIFT and Craig Ramsey - Head of Real-Time Payments at ACI Worldwide.
How to be a Payments Trailblazer – The Seven Habits of Highly Innovative Organizations
The new Culture of Innovation Index from Ovum and ACI identified segments—from banks to intermediaries to merchants to corporates—at the cutting edge (of innovation) across the payments ecosystem. But what is most notable about those segments that have reached ‘trailblazing’ status is the apparent lack of commonality between them. No one segment, nor one region fosters better innovation. In fact, what’s driving these segments/organizations to be best of breed is their own culture of excellence. The only thing they have in common is their attitude.
How will SWIFT gpi Impact Latin America?
As the world continues to transition toward real-time, and technology continues to evolve, new challengers are disrupting the market with value propositions including real-time cross- border payments. The competition has inspired SWIFT to work with the industry and challengers to create the Global Payments Innovation (GPI) program, which radically changes the way banks interact with their correspondents and offers improved transparency and customer service to their customers.
The Middle Eastern payments revolution: Getting Real-Time Ready
The Middle East is developing quickly and considerably. The population has surpassed 410 million and a number of nations, such as Saudi Arabia and the United Arab Emirates (UAE), represent some of the world's most innovative economies. The region has become synonymous with the rise of large infrastructure developments and technological innovation, while tourism continues to grow - 1.4 billion people visited in 2018 alone.
Why India's Payments Players Need to Fight Fraud with Machine Learning
By 2023, experts are predicting 60 billion UPI (Unified Payments Interface) transactions annually, accounting for more than 50 percent of India’s total digital payments transactions. And it’s estimated that today nearly 50 percent of all real-time payment (RTP) transactions globally are processed in India. It’s an exciting market for payments innovation, with a wide range of digital overlay services available to consumers and merchants, thanks to the introduction of UPI.
The Untapped Opportunity of Machine Learning for Real-Time Payments Fraud Prevention
Artificial Intelligence (AI) is among the buzzwords of the moment, but when it comes to tangible innovations that have the potential to drive rapid ROI, machine learning should be part of every bank or processor’s strategy. No matter the size of the institution.
European Banks Have the Right Tools to Stay Ahead – But Will Big Tech Overtake?
Open banking and immediate payments have come a long way, according to the panelists who joined me during the ‘Open Banking in an Instant World’ session at EBAday in Stockholm recently. The building blocks are now falling into place through the introduction of national and regional schemes, open banking initiatives, regulations such as PSD2 and the acceptance and use of APIs.
How UPI is Driving India's Shift from Cash to Digital Payments
The Indian economy has traditionally been heavily dominated by cash, while experiencing low adoption of various online payment systems including National Electronic Funds Transfer (NEFT), Real Time Gross Settlement (RTGS) and inter-bank mobile payments. The dominance of cash is evidenced by the ratio of cash withdrawals at ATMs vs debit card usage at Point of Sale (POS)—ATM transaction volume is more than 2x greater than POS.
Regulating for Real-Time: The Role of Government in Payments Modernization
Dr. Leo Lipis and Craig Ramsey, Head of Real-Time Payments for ACI Worldwide, continue their discussion on real-time payments and the findings of the new white paper, Get More from Real-Time.