Gain more loyal customers, reject only fraudsters
Nethone has developed a proprietary fraud prevention solution based on a Know Your Users™ approach, which enables comprehensive, in‑depth, multidimensional profiling of all online users. From knowing customers to understanding their real motives ‑ it’s an essential tool for the new era of customer‑centric services.
is an answer to this challenge
We’ve built Nethone Profiler, a solution that allows us to collect unique first-hand data about online users.
Thanks to the proprietary use of Machine Learning techniques, we are able to profile gathered information, segment traffic and block fraud attempts.
We deeply believe that the future of e-commerce will mean less and less online friction for users. Years of experience in online business allowed us to understand how much of the user-side friction is caused by imprecise risk management processes. Nethone has been created to enable the further dynamic growth of the e-commerce channel, thanks to radically reducing the risk management related friction - manual verification and passive authentication.
From knowing to understanding
What’s the difference between Know Your Customer (KYC) and Know Your Users™ (KYU)?
KYC tries to recognise who’s on the other side of the screen ‑ verifying the
identity of a customer. But why not use this data for other purposes also?
What if we could:
These questions have led the Nethone team to where we are today.
How to shift from KYC to KYU?
To build on top of Know Your Customer towards Know Your Users™ and benefit from that upgrade, it is crucial to understand a few things. First of all, being customer‑centric ‑ it’s the users who need to be satisfied with their online experience to become loyal clients. Second of all, Machine Learning models are a key factor to this change.
ML models developed for years
We have been working on our solutions to bring an added value of increased conversion rates since 2016. It required not only a good infrastructure, but also Data Science expertise. All to train Machine Learning models dedicated to fulfil the specific needs of each of our clients.
And it’s important to understand that these models can actually reinforce each other by leveraging the outcomes of analyses conducted in the past or at the very same time, but in different contexts for new analyses.
More accurate predictions
Just to illustrate the idea; a model identifying prospective frequent shoppers can generate predictions to be used as an additional source of data for a new model, responsible for, say, detection of users likely to churn within 3 months to make their predictions more accurate, and so on and so forth.
Creating an ecosystem of models is quite a challenge and requires the involvement of some of the brightest minds – people who understand all the business nuances as well as technical requirements. Our dedicated teams take care of this challenge to address even the most complex needs.