Nethone is a machine learning-based fraud prevention SaaS company that allows online merchants and financial institutions to holistically understand their end-users—also referred to as “Know Your Users (KYU)” in industry parlance. With its proprietary online user profiling and ML technologies, Nethone is able to detect and prevent payment fraud, account take-overs with unrivalled effectiveness. Founded in 2016 by a group of security experts, financial business executives and data scientists within Daftcode - a Poland-based venture builder, is today successfully cooperating with 100+ global e-commerce, digital goods, and financial industries. In 2021 Nethone was named Poland’s fastest-growing company in the ‘Deloitte Technology Fast 50 Central Europe’. Nethone Guard Nethone Guard is our proprietary machine-learning based product designed to protect the entire user journey, from onboarding to post-payment, at the same time helping 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 Guard is built on four pillars: 1) Profiling solution With this proprietary tool, we bring more value to the payments and commerce industry than other fraud prevention solution providers in the landscape. We extract exhaustive user profiling data from any device while the user interacts with our client’s online environment via a javascript code embedded inside of the website or via an SDK embedded in the mobile app. We get more context information about each session, and we go beyond data that is made available by the user. This enables us to gain a deeper understanding of each session and identify potential fraud threats more effectively. Each session gathers over 5,000 in-depth data attributes - unique hardware, software, device, network, and behavioral, and device fingerprinting data. Examples of attributes: device motion: gyroscope, accelerometer, magnetometer; Current battery, CPU and disk space state; language, currency, timezone, and country; static hardware and system available information, and many more. Our device fingerprinting process involves selecting a set of attributes from those 5,000 to create a fingerprint that points to a particular device. Importantly, this fingerprint is not saved on the device itself, but is instead determined by looking at the device's configuration. This ensures that the fingerprint cannot be deleted from the device. Additionally, we use multiple fingerprints to account for both persistent attributes (e.g. CPU, processor) and changing attributes (e.g. Wi-Fi). 2) Data hub The data hub allows us to combine all the knowledge acquired around the user’s session within the Profiler with more data provided by our client, which can regard information such as characteristics about the product, the ticket value, the brand, the shipping address etc. We also integrate with some other services such as Ekata, to enrich our knowledge, all via a single API. 3) Machine learning-powered decision engine The user data collected is combined with additional data in order to extract more hidden knowledge that could reveal the true intentions of a particular user. Our machine learning-based decision engine finds patterns that point to fraud and then reveals this to our client as a recommendation. We’ve built predictive models so we can use them to come up with a recommendation or an assessment of fraud risk in real time. The decision engine delivers three recommendations for our client to decide: accept, review, refuse. The decision logic is under our clients’ control, so they can control the models whenever they want and influence it with the changes of the rules. 4) Dedicated Data scientist and Customer Success Manager Enterprise merchants, which deal with large volumes of transactions, need more human intelligence support. Our data scientists are assigned to collect business insights from our customers and create, manage, and calibrate the models for the clients. Together with the CSMs, they serve as the first line of contact when it comes to answering questions, modifying the model configuration, or any other relevant activity that aims to deliver the best performance for the client’s business needs. Nethone Alerts Alerts provide early notification and the ability to refund a transaction within supported card schemes, such as Visa, Mastercard, Discover, Diners, AMEX, CUP, and JCB. We seamlessly integrate Ethoca and Verifi chargeback alerts to automatically protect your accounts from unnecessary fees or threat of suspension. Benefits: • Merging two services ( Ethoca and Verifi) allows for less integration and faster reaction time to possible fraud. • Nethone matches particular transactions with alerts and serves you a full scope of transaction insights. • All alerts are 100% confirmed between the card issuer and the cardholder. • Pay only for the chargeback alert that has been used. • Avoid chargebacks as well as shutdown compromised accounts and suspend services. • Prevent receipt of duplicate alerts (and additional fees). Avoid the chargeback procedure and disputes In a standard path, a potential chargeback is raised either by a customer or because someone used the card to commit fraud. The procedure goes through many stages and can take up to 3 months, generating additional costs. We collect all alerts and match them with your transactions. We use our API to send you summarized information about what triggered the alerts, then you can refund the end customer to avoid a chargeback claim. We send to our chargeback alert providers Ethoca or Verifi all the notification feedback from you while they transfer the outcome to the issuer, officially closing the case. Nethone PSD2 There is currently a high challenge rate and low exemption usage in the ecommerce space. We come with the opportunity of bypassing any friction that may come with SCA, including soft or hard declines, while keeping fraud prevention at the same high standards for your business and consumers. Our proven holistic approach to user profiling leads to low fraud rates with safe user traffic eligible for SCA exemptions. Benefits: • Increased customer conversion through frictionless UX • Full anti-fraud capabilities despite the use of SCA exemptions • Increased revenue potential driven by customer loyalty and retention • Reduced bad rates: cart abandonment, false declines, failed transactions We assess the probability of fraud for each transaction. Moreover, we extend our service to detect fraud with a high or low probability, and then issue a TRA exemption as a result. As part of our solution, we essentially perform: • Real-time checks addressed by rules and powered by our ability to identify device and network anomalies, and notify about signals that indicate a high probability of fraud. The number of signals we have is constantly changing based on our intelligence-gathering capabilities, and new features are added on a regular basis. • Risk analysis of the risk-based factors covered by the directive, which can be performed either by using rules or custom machine learning models according to your service tier offering or traffic volume. Our automated tools track behavioural patterns and identify signals in real-time, based on the user's interaction with the browser or mobile app environment. Our machine learning model takes into account the user's payment history, geolocation, signals, and other relevant features to provide detailed and reliable recommendations. As a result of collecting all the necessary data, we are able to accurately determine whether a transaction belongs to the ‘Trust’ category. Otherwise, you may choose from the accept/review/refuse lists, rules and models, and create your own setup. Nethone KYC In partnership with Authologic, we streamline the KYC compliance efforts with an automated capability that shows the right way forward to various ID verification methods and allows you to choose from a variety of KYC solutions, rather than committing just to one. As a response to your needs, we provide you with guidance on when to discontinue compliance checks, and remove manual reviews of suspicious users while enhancing UX for genuine ones. Benefits: • Make no unnecessary efforts. As soon as we detect fraudulent users, we don’t go further with KYC checks, thus saving you time and money. • In real time, we ensure that only legitimate users pass through and inform you that your current and potential customers are on the sanctions or PEP lists or present in adverse media. • Our user score derived from our Profiler and any additional data provided by you allows you to guide trustworthy users to a faster verification process. The faster the ID verification process, the faster you’ll see your customers fully onboarded. • Localization is key for customized experiences and complaint procedures. Authologic makes sure that users’ KYC checks are on par with their country-specific requirements. • Thanks to our KYC & AML data and knowledge about the user, we can automatically validate KYC checks if enhanced verification is required. Flexibility to build tailored paths for every customer journey The risk level for each interaction may be interpreted differently, according to each users’ case, so it is wise to treat each transaction as unique. Our risk-based approach enables recommendations depending on the pre-scoring results. For example, bot detection is a fraud sign, but also a reason to save time and money. In such a situation, we don’t recommend going further with KYC check. Moreover, every decision and recommendation is transparently justified by our white box ML, so you’ll know what exactly made us reject a user and why. With our profiling tools and additional data provided by the customer (such as the registration form or transaction amount), we measure the fraud risk, and, based on the results, we send the user to a defined KYC method as follows: • A bad score will send the users through a full strict KYC • A mid score will send the users through a simplified KYC • A good score will send the users through a simplified KYC and allow them to authenticate using the methods put at the user’s disposal as per the list below - ID verification + liveliness: Upon selecting the selfie/biometrics method, users are asked to scan the document front and back, check the picture’s clarity, take a liveness test with the selfie, and complete the process. - Government ID: Users select the Digital ID method, open the digital ID app, enter PIN, touch the document to the phone (NFC), and complete the process. - Open Banking: Users select the Open Banking ID method and their bank from the lists provided, approve PII transfer in the bank, and complete the process. - Bank ID: Users select the Bank ID method and their bank from the lists provided, approve PII transfer in the bank, and complete the process.