Fraud never stays still.

ONLINE.KYC’s machine learning models adapt to meet existing and new threats so your business can add more customers with no more risk.

Connect the dots

See the bigger picture

A frictionless experience

for good users

A frustrating one

for fraudstersGlobal

Securing online sales

ONLINE.KYC is a fraud detection system that uses Machine Learning models and other techniques to form a complete picture of a shopper’s risk profile before they check out. ONLINE.KYC provides real-time decisions so your merchants can accept payments confidently, protecting their margins while helping you to reduce fraud across your portfolio.

Online.KYC.org uses a combination of technologies to identify and reduce risks to online businesses. Machine Learning, graph networks, and a full-featured rules engine provide the technical underpinning to a winning fraud strategy. When great technology meets great online sales website the result is a business that can grow with confidence knowing that it can trust the users it is adding and the payments it is collecting.

Machine Learning algorithms use AI techniques to make highly accurate predictions about events in the real world. The algorithms identify patterns in large volumes of data and become more accurate as they receive feedback on previous forecasts.

This feedback is provided by combining hard data with human insight. The unique ability of fraud analysts to spot trends and deal with hard cases rapidly improves the algorithms’ accuracy.

Machine Learning Finds More Fraud Faster

Machines are better than humans at dealing with large data. Our models use hundreds of data points across a user’s purchasing journey to determine if the customer is genuine. The ONLINE.KYC fraud detection models have been developed to detect fraudulent e-commerce and fraud transactions as quickly as possible, to prevent significant fraud loss from an account.

Machine Learning allows merchants to get results, fast. Our model returns results in microseconds - letting good customers through quickly with zero impact on their journey.

As your customer base grows and the volume of data increases, Machine Learning techniques allow you to avoid increasing operational costs whilst keeping fraud rates down.

Every company’s fraud problem is unique. Machine Learning allows us to provide adapted models specific to your threat, taking into account your conversion goals and your risk appetite.

Getting all the benefits out of Machine Learning is dependent on large volumes of good quality data sent via a robust and secure integration.

The rule-based approach.

Fraudulent activities in finance can be detected by looking at on-surface and evident signals. Unusually, large transactions or the ones that happen in atypical locations obviously deserve additional verification.

Purely rule-based systems entail using algorithms that perform several fraud detection scenarios, manually written by fraud analysts. Today, legacy systems apply about 300 different rules on average to approve a transaction. That’s why rule-based systems remain too straightforward.

They require adding/adjusting scenarios manually and can hardly detect implicit correlations. On top of that, rule-based systems often use legacy software that can hardly process the real-time data streams that are critical for the digital space.

Effective rules provide important boundaries for Machine Learning models. Create and test rules on the ONLINE.KYC platform to ensure that relevant business policies are taken into account when evaluating a customer.

A Machine Learning-based fraud detection

A Machine Learning approach outperforms traditional rules-based strategies through unbiased adaptation to changing events.

Machine learning allows for creating algorithms that process large datasets with many variables and help find these hidden correlations between user behavior and the likelihood of fraudulent actions. Another strength of machine learning systems compared to rule-based ones is faster data processing and less manual work. For example, smart algorithms fit well with behavior analytics for helping reduce the number of verification steps.