Criminals used to rob banks. They also held up cash-in-transit vans, casinos, and betting shops. That is where the money was. Nowadays, data equals money, so heists and hold-ups have gone digital, so much so that global losses from online payment fraud more than doubled between 2018 and 2023.
In this article, we will further explore how graph analysis weaponises the criminals’ network against them to help prevent and even pre-empt online fraud.
Card fraud used to be lone opportunist thieves intercepting cards in the mail, or chancers committing lost/stolen fraud against individual consumers or small retailers. By the 1990s, fraudsters found basic knowledge and worked in small teams to counterfeit or skim cards, mostly domestically.
By the new millennium, bigger gangs were targeting larger retailers and all types of customers. Fraudsters had more technical know-how to steal card data and identities remotely and hacked humans via phishing and other social engineering scams.
Nowadays, card fraud is committed by international crime gangs on an industrial scale. They target multi-national businesses, together with the banks and payment service providers behind them. Using technical expertise, they jackpot ATMs, take over accounts, and compromise card data. They utilise insider knowledge to hack business processes for chargebacks, refunds, affiliate referrals, etc.
Currently, card fraud is a USD 40 billion a year problem, set to rise to USD 48 billion by the end of 2023. Much of this is borne by businesses if they have already shipped the goods or provided the service. Online businesses cannot hope to fight modern-day fraud with old methods and mindsets, so a new approach is mandatory.
Individuals’ fraud campaigns increasingly rely on a long value chain of bad actors to support and monetise them, and a shared criminal infrastructure, i.e., stolen identities, compromised accounts, fake profiles and addresses, and money mules. This strength in networking can be weaponised as a weakness, which is where graph analysis comes in. Graph analysis seeks to understand the relationships between linked entities in a network. Businesses can use it in fraud prevention to help them know their foe by their ‘A-B-C’: actions, behaviours, and connections, as in Ecommpay’s solution.
Graph analysis can identify and stop multiple, connected instances of fraudulent behaviour by spotting suspicious patterns, such as unexpected or unusual links.
Figures 1 and 2 visualise various fraud rings, with the red nodes depicting confirmed fraudsters. The system blocks the red nodes and other connections in the chain. It neutralises the threats until the criminals stop. If new connections join the chain, or criminals try to start a new chain elsewhere, graph analysis can spot this, flag it for investigation, or shut it down.
Since early 2022, Ecommpay graph analysis has revealed nearly 13,000 fraud chains, involving 50,000 connections across 200 unique merchants. Nearly one-third (29%) were confirmed fraudsters, while others were part of unreported or unsuccessful fraud attacks.
With so many anti-fraud solutions on the market, how do online businesses decide what is the right one for them?
Flexibility and customisation. How an ecommerce retailer or online travel business experiences fraud is different from a fintech, so you must tailor a solution that makes sense to your business, without adding extra friction to it. The aim is to maximise conversion while preventing fraud. Ecommpay has 60+ anti-fraud filters for businesses to customise, according to limits, restrictions, and scenarios.
Unified service. Taking acquiring and fraud prevention services from a single provider helps avoid multi-supplier headaches and may also lead to better fraud detection. Alerts are less likely to fall between the gaps of fragmented systems when the service is all-in-one and comes from a single place. Unlike many providers, Ecommpay has built a proprietary Risk Control Management System in-house. This gives us full control over the customisation of anti-fraud filters depending on individual customer needs, which, in turn, helps deliver high conversion rates and maximises revenues.
Self-learning. Ecommpay’s graph analysis relies on a self-learning element, so it can predict new fraud attacks. The models and analysis also improve with time and data, meaning businesses can add historical data to improve future fraud detection and stop dormant fraudsters by pre-empting possible fraud strikes.
Layered approach. The best anti-fraud solutions take a holistic approach with a mix of different technologies, for example, automated monitoring powered by AI, combined with traditional rules-based techniques and manual interventions. Graph analysis adds another layer of protection to Ecommpay’s already sophisticated offering, comprising machine learning, automated monitoring, black/whitelisting, and manual reviews.
The human touch. By combining real, human minds and the help of machines, we can deliver better fraud prevention solutions. Ecommpay provides a dedicated anti-fraud manager to add human insight and round-the-clock support to already powerful machine capabilities. This approach delivers a 0.2% fraud-to-sales ratio, with no disruption to customer journeys or genuine customers.
As befits serious organised crime, card fraud and fraudsters are serious and organised. They network well, which modern machine-learning techniques, such as graph analysis, can detect. Deploying anti-fraud solutions that are tailorable, self-learning, holistic, and human gives businesses the edge in the fight against online fraud. The future of fraud prevention is not acquiring extra security but securing acquiring. After all, the best fraud protection is unobtrusive. Ecommpay delivers seamless fraud protection with its payment-acquiring products. No more acquiring-plus-security. Just secure aŃquiring.
This editorial is part of The Paypers' Fraud Prevention in Ecommerce Report 2023-2024, the ultimate source of knowledge that delves into the world of fraud prevention, revealing the most effective security methods for companies to stay one step away from bad actors and secure their businesses.
Ecommpay is an entire fintech ecosystem, allowing businesses to make and receive online payments globally. Founded in 2012 and headquartered in London, Ecommpay combines direct acquiring capabilities, 100+ alternative payment methods, mass pay-outs, a proprietary, in-house Risk Control Management System, and more, within a single unified integration.
Every day we send out a free e-mail with the most important headlines of the last 24 hours.
Subscribe now