As part of our fraud prevention efforts, we monitor and check four user journey stages. The first step regards user acquisition, where consumers get in touch with the product, service, or brand. For us, it’s relevant to know the interaction channel – browser or mobile (Android and iOS) – and the users’ true intentions. We usually detect high levels of bot activity at this stage.
The second step is ‘login and registration’, meaning the user has entered their details (name, address, email, etc.) and is ready to start shopping. Recurrent user logins are also checked for fraud. After this, the customer completes the transaction through the checkout process. In several instances, the fourth stage occurs when consumers initiate transaction disputes asking for refunds.
The issues that are most likely to arise are related to fraud and UX. A cumbersome authentication process can alter or stop the buying journey and make consumers take their business elsewhere. So, there is a hassle for the consumers, but also a loss for the merchant. The image below illustrates the most prevalent types of fraud that can occur at each stage in the user life cycle. Some of them, such as account takeover (ATO), identity fraud, or synthetic ID fraud, primarily affect the end user.
Consequently, the problems above also affect merchants. Moreover, ecommerce businesses are also faced with affiliate fraud, ATO, promo and policy abuse, return fraud, and first-party misuse. These types of fraud are common in the industry, so we are not dealing with a new phenomenon, but rather with a persistent one that carries severe consequences beyond friction and false positives.
Besides revenue loss, ATO can lead to a damaged brand reputation. Promo and policy abuse can force merchants to tighten the rules, thus, discouraging loyal customers from shopping with them. Chargebacks and first-party misuse are not only about paying fees associated with disputes, but about being subjected to card schemes monitoring programmes that come with hefty penalties.
Our presence at every step of the user journey enables us to address each type of fraud along the way. Thanks to a modularised approach, we are also flexible enough to meet specific challenges that ecommerce businesses fight with. For example, ecommerce merchants can take advantage of SCA-related exemptions to optimise their payment processing setup, resulting in higher conversions – if we determine a transaction is safe, 3DS is not required.
Moreover, to spare merchants from dealing with chargebacks, we activate our early chargeback notification alerts (powered by third-party providers); if we detect fraud, the transaction is simply rejected, and in case of legit requests, merchants can quickly refund the consumer, so no dispute is necessary.
The synergies between our products enable us to detect risks, offer end-to-end protection, and provide risk-based KYC in the same solution. Any business that requires thorough ID verification of their users can encompass fraud detection, KYC, and AML, under one API. In response to the risk assessment that we undertake, the user is guided to either a hard or a soft check. The key benefit we're offering here is that the journey stops when fraud is detected. For instance, in the case of bot detection, we don’t recommend further KYC checks, thus saving time and money for our clients.
Behavioural biometrics keep the balance between user convenience and protection. Device movements are analysed in the background, and we can detect anomalies and bot activities in real time. Yet, the most valuable aspect is determining where the suspicious behaviour comes from, so one can proactively act on any attack targeting their business. Our intelligence team frequently explores the dark web to discover new signs of fraud based on behavioural biometrics. Fraud can be sophisticated, but is also characterised by cheap and unskilled labour, such as click farms.
Apart from the flexibility that it offers to businesses looking to employ just one or multiple parts of the entire product, a modularised approach is, indeed, capable of customising the user journey through a fast and safe path toward the checkout.
The trend is dictated by more and more companies embracing this model, but we aim to stand out from the current reality by offering a ‘try-it-for-free-and-onboard-yourself’ tool. This will allow anyone interested to enrol in a free trial that walks them through the product's main features so they can have an accurate picture of how it works and how it can benefit their specific needs and challenges.
This editorial is part of The Paypers' Fraud Prevention in Ecommerce Report 2022-2023, 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.
Maciej is an experienced manager focusing on building data products. His vast experience covers actuarial science, data science, data and software engineering.
Before joining Nethone in 2018, he worked at Deloitte and EY delivering advisory services for insurers in the EU (risk and actuarial). At Nethone, initially, as the Head of Data Science, is responsible for delivering the best-modularized fraud prevention and risk detection platform to Nethone’s global customers.
Maciej holds a Master's degree in Quantitative Methods in Economics & Information Systems from the Warsaw School of Economics (SGH).
Nethone is a machine learning-based fraud prevention SaaS company that enables ecommerce merchants and financial institutions to holistically understand their end-users — also referred to as Know Your Users (KYU). With our proprietary online user profiling and AI-powered tools, we can block all risky users without friction to the good ones by exhaustively screening every single one.
Nethone is also part of the MangoPay Group, a pan-European provider of platform payment & wallet infrastructure, to offer enhanced anti-fraud capabilities catered to marketplaces and platforms.
Every day we send out a free e-mail with the most important headlines of the last 24 hours.
Subscribe now