Overview

A powerful and modern artificial intelligence engine transforms data into an optimal and precise predictive model that allows users to explain the causes and consequences of a particular fraud. It stands out from other solutions due to its accuracy and power.

Thanks to its predictive engine, it uses new data from customers' transactions to learn and constantly improve its accuracy without human effort. This ongoing process allows the detection and faster adaptation to new defrauding schemes that may arise, significantly reducing potential losses.

Capabilities

• dVelox EFM is based on predictive models that allow it to "explain" the causes that have brought about a certain type of fraud.
• It is a tool sensitive to changes in market behavior that automatically adapts to them, detecting new defrauding schemes, as they arise at every moment, to anticipate them and make decisions proactively.
• It detects fraud accurately and nearly in real-time (on-line). Its results back it:
  • A 35% average increase of fraudulent transaction detection.
  • 10% of the fraudulent transactions detected were previously unknown fraud.
• It gathers new feedback data from customers' operations unattended and automatically.
• The business user creates his own scenarios and simulations, using an intuitive and graphical interface that allows him to work autonomously without depending on the math or computer departments.
• Ease of integration with corporate applications and architectures. Being based on standards it allows new functionalities to be added according to business needs.
• Detection of fraudulent behaviors without requiring an extensive data history. The tool gathers feedback automatically and is continuously learning thus improving its accuracy as time goes by.

Added Value

• Reduction of losses caused by fraud. Economic losses are reduced by detecting fraud in less time.
• Full real-time analysis coverage to give automatic support to the whole fraud detection cycle. Up to a 10% increase in the detection of previously unknown fraud.
• Reduced analysis operating costs. The reduction in the amount of alerts and false positives allows for a decrease in analysis costs by decreasing incidents that not only are non-fraudulent, but in which the rules, in most cases, act because they are not up to date.
• Cost Reduction of creating and maintaining models. Complex and accurate models may be built in hours instead of weeks or months. SSuch immediate results make it possible to activate the mechanisms of prevention and research.
• Nearly real-time reaction capability to new types of fraud. Compared to other existing technologies based on reactive strategies, dVelox Fraud Management is able to gather data daily to detect suspicious behavior at the speed the market needs.
• Its ease of use enables greater independence of specialized personnel from business rules and analytic tools that require the knowledge of a team of experts.
• Its Ease of use facilitates greater independence of business rules expert and analytic tools that require the intuition of a team of experts.