How do we work?

The Features Analytics modeling process goes through six stages to build sophisticated machine learning models for your needs.

 

The six stages are:

 

  • Data gathering and pre-processing
  • Data analysis
  • Data enrichment: Feature design and calculation
  • Data segmentation
  • Machine learning model development per data segment
  • Model optimization and delivery

 

We build not one single model but multiple models to match your needs or desired KPI’s.

 

Features Analytics supports both real-time and batch data feeds with three different API based deployments.

 

 

eyeDES® one model does not fit all

eyeDES® - Advanced Modeling Technology

Our predictive modeling technology detects and identifies highly complex data relationships and correlations to allow state-of-the-art fraud detection within a variety of payment contexts. The principles of this technology were originally developed and implemented successfully in the medical sector. Utilizing sophisticated algorithms, statistical analysis and pattern detection this technology that was once used to predict the likelihood of cancer is now available to evaluate financial event risks and detect payment fraud.

 

 

 

 

Custom Models that evolve with the data

Herein lies one of the key aspects of Features Analytics and eyeDES® technology. We analyze and enrich your data with features able to find hidden patterns in the data. These features evolve with the data in real-time. Therefore, our predictive custom models, built on top of your feature enriched data, will evolve not only with the patterns of the fraudsters but also with the behaviors of the genuine customers.

 

eyeDES®, your advanced risk and fraud management solution

eyeDES® can be utilized by different types of organizations, from eCommerce merchants to acquirers, processors and issuing banks. With our focus on custom modeling and features specific to your organization, we can dramatically improve your fraud detection capabilities. No single variable or feature can fully discriminate between fraud and non-fraud records. Only by combining several of them and applying state of the art machine learning algorithms complex behavior patterns and trends will become apparent.

 

One model does not fit all

eyeDES® delivers multiple models to different segments or channels of your business. This could include separate models for different countries or regions, or different levels of risk based on factors such as customer age or purchase amount. These models can be applied in addition to or in place of analytic models your organization may have in place, each providing a risk score and reasons contributing to the transaction assessment. The level of performance can be maintained or improved for each model segment, in contrast to fixed models that utilize all transactions indiscriminately. The right combination of the models will deliver an overall optimum performance of your solution.

The Features Analytics modeling infrastructure allows us to rapidly implement, test and decide on the multitude of possible features, data segments and machine learning algorithm combinations. So, package of models offering maximum performance can be delivered within a limited amount of time.