Ravelin is a  UK company that provides payment fraud protection for online businesses.

Established late in 2014 by ex-employees in charge of fraud at Hailo, the transport app, the team recognised that the combination of machine learning and graph networks was the best way to combat the increasing number of fraudulent payments faced by on-demand, real-time businesses.

Ravelin helps organisations reduce losses and increase revenues by enabling more genuine orders to be accepted through the innovative application of leading technologies. By integrating with a business’ website or mobile app to get a real-time feed of customer data, a machine learning model can provide the client with probabilistic scores of the likelihood of the customer being fraudulent. Machine learning allows us to do this in less than 500ms guaranteed, which means our clients can be assured they are being protected in real-time. We also employ graph networks analysis so we can discover connections within a merchant’s network and across Ravelin’s network of merchants. This allows us to identify and block whole networks of fraudulent accounts, therefore quickly and efficiently stopping fraud from spreading.

The application of these artificial intelligence techniques and highly efficient graph database approaches is Ravelin’s true innovative USP.  Built by a small team of fifteen developers and data scientists, we take established academic best practice and apply it to solve real-world problems for our clients. 

Our customers have access to the data science capabilities that industry heavyweights like Google and Apple use, but have made it available to any business. The product’s sleek design disguises the complexity of the underlying tech and makes it not just affordable but consumable, comprehensible, and actionable to a non-specialist user base. 

Ravelin helps online businesses reduce losses and increase revenues by enabling more genuine orders to be accepted through the application of leading technologies. By integrating with a business’ website or mobile app to get a real-time feed of customer data, a machine learning model provides the client with probabilistic scores of the likelihood of customers being fraudulent. Machine learning allows us to protect our clients in real-time as scores are delivered in under 500ms guaranteed. We employ graph network analysis to identify and block whole networks of connected fraudulent accounts, within a merchant’s database and across Ravelin’s network of merchants.