Ari10 Fraud Protection Case Study | Nethone
nethone fraud ocean hero background


Ari10 (formerly Bitcan) is a crypto exchange which allows for instant cryptocurrencies transactions of up to USD 13,500. The most frequently chosen payment form in this exchange is so-called pay by link. Unfortunately, the simplicity and convenience of pay by link does not always go hand in hand with security. Therefore, the biggest challenge Ari10 faced was increasing the security of transactions, especially in this area of payments.


High percentage of fraudulent transactions
High percentage of fraudulent transactions

Despite applying advanced Anti-Money Laundering procedures for registration purposes,crypto exchanges and wallets are not secured enough when it comes to transactions. A high percentage of fraudulent transactions and instability in fighting fraud result in lowered trust in wallets and exchanges from banks and payment service providers. Thus crypto companies seek solutions allowing for instant user verification without a manual review.

Too many transactions rejected
Too many transactions rejected

One of the common practices is rejecting users who appear suspicious at a glance. However, sometimes they happen to be legitimate customers. It is crucial to limit the number of these mistakes and to catch fraudsters, blocking a minimal percentage of transactions.


Nethone proposed a proprietary script embedded on the client’s website, which has been extracting over 5,000 attributes about each Ari10 customer--fingerprinting their device and checking their behavior to spot any repetitive patterns and abnormalities that may imply fraud.

The very first step in cooperation with Ari10 was to reduce the high fraud rate as quickly as possible by implementing the rules that block the most common and strongest fraud cases.

Then Nethone closely observed and analysed the traffic to fuel the first ML model with proper data and to train it. That allowed for not only to fight fraud cases with much better accuracy, but also to reduce the number of good users blocked by the initially implemented rigid rules. This example again proved the superiority of ML models over static rules but also showed that their hybrid use has its benefits depending on the situation.

Currently, models are constantly refined and modified by a dedicated Data Scientist, based on the acquired knowledge and close cooperation with the client.

2-month results

Reducing number of blocked traffic
Unauthorized transactions reduction
Total worth of prevented fraudulent transactions

Secure your wallet or exchange!

We’ll prepare a solution focused on the singularity of your business. Choose your favoured date and time and speak to a member of our team.

... or leave your contact details so we can get back to you.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Financed by: