Risk Ident

Risk Ident offers anti-fraud solutions for global companies within the e-commerce and financial sectors.

RISK IDENT is a software development company base in Germany and the US that offers anti-fraud solutions to companies within the e-commerce, telecommunication and financial sector. We are experts in data analytics and machine learning. Our key products are FRIDA Fraud Manager, DEVICE IDENT Device Fingerprinting and EVE Evaluation Engine. Uses cases include payment fraud, account takeovers, fraud within account and loan applications. FRIDA is the all-in-one solution for intelligent fraud prevention. All customer transactions will be automatically filtered and analyzed by using a self-optimizing set of rules. It will use powerful machine learning algorithms to re-evaluate every rule based on success rates. FRIDA is a software solution that complies with highest data privacy standards, all components can be quickly integrated locally in our customers own infrastructure. FRIDA sets new standards in user experience. All data can be easily visualized. There is no steep learning curve for the fraud prevention team, FRIDA can be mastered after a few hours of training. And FRIDA will learn by every new fraud case, automatically adapting to new fraud patterns without any additional configuration. DEVICE IDENT offers the most sophisticated device fingerprinting technology on the market today. Efficient rule sets calculate a risk score to every device within milliseconds. Push mechanisms will immediately alert you of fraud cases. Furthermore, all data can be easily obtained via an API to include it into your fraud prevention processes. DEVICE IDENT fully complies with EU data privacy laws. EVE is a flexible platform to cover different aspects of risk management for any kind of transaction evaluation. It applies selected machine learning algorithms to evaluate different input streams for a real-time risk assessment: EVE can be trained with historical data but will improve automatically by evaluating and adapting to new fraud patterns.