Article Top Ad
Reading Time: 3 minutes

Fraud and Data Science teams now have expanded control and
transparency to leverage advanced tuning capabilities to build
fully-optimized fraud models for their organizations

the leading fraud detection company with solutions powered by
transformational AI technology, announced today it has strengthened
dCube with the additional levers for modeling and tuning, and enhanced
data management functionality. dCube is DataVisor’s flagship fraud
management solution, combining advanced machine learning capabilities
with enterprise workflows to put full control in the hands of fraud and
data science teams to proactively defeat fast evolving fraud with speed
and agility.

New optimization capabilities offer unparalleled levels of control and
flexibility to build bespoke models optimized for the unique fraud
management needs of any organization. With added ETL capabilities, teams
can go beyond primary data validation to fully integrate, manipulate,
and enrich data before modeling, to ensure peak performance. In
introducing these enhancements to dCube, DataVisor brings to the fraud
landscape the most powerful and adaptive AI-powered fraud solution
available today.

Advanced Optimization Capabilities for Model Tuning

Fraud modeling with enhanced optimization capabilities means
transparency and total ownership of the models’ teams build. This
includes the ability to integrate organizational domain expertise into
the model building and feature engineering processes. Just as proactive
detection and automated model development represents a quantum leap
forward from legacy fraud solutions tethered to labels, rules, and
manual review, these enhancements further push the envelope by
introducing an intelligent optimization mode that offers access to a
wide range of additional parameters to further precision and recall.
Teams can now tune fine-grained model parameters including feature
similarity threshold, cluster size, correlation features, and more.

Enhanced ETL Capabilities

Teams can now enjoy additional layers of control over the pre-modeling
process to ensure the highest quality data, no matter the range of
sources, formats, and data types. While dCube retains its core upload,
mapping, and validation capabilities, these new enhancements enable new
levels of interactivity, giving teams the ability to analyze, transform,
and join together data in fine-grained ways within the platform. This
includes being able to integrate and organize internal and external data
sources at scale.

Production Deployment and Monitoring

dCube now features additional model deployment and production monitoring
capabilities. During deployment a user can configure a start date for
the model in production and mirror the settings in the model development
phase. After deployment, to make sure the model is running as expected,
production health can be monitored using the received data trends and
detection results.

Once in production, organizations will now enjoy additional compliance
benefits as well, with the assurance of end-to-end record keeping. “As
tech savvy fraudsters become increasingly adept at blending in with
normal users to evade detection, organizations need better ways to
analyze data, and more nuanced approaches to find actionable insights,”
said Dr. Yinglian Xie, chief executive officer at DataVisor. “With
these enhancements, dCube delivers organizations the capability and
control to make decisions based on real-time results to prevent known
and unknown fraud before financial and reputational damage can occur.”

To learn more, DataVisor CEO and co-founder Dr. Yinglian Xie will be
presenting at Money2020 Europe on June 5th at 2:10 PM on the
Industry Transmutation Stage, find more information here.

About DataVisor

DataVisor is the leading fraud detection platform powered by
transformational AI technology. Using proprietary unsupervised machine
learning algorithms, DataVisor restores trust in digital commerce by
enabling organizations to proactively detect and action fast-evolving
fraud patterns, and prevent future attacks before they happen. Combining
advanced analytics and an intelligence network of more than 4B global
user accounts, DataVisor protects against financial and reputational
damage across a variety of industries, including financial services,
marketplaces, ecommerce, and social platforms.


Sarah Shkargi
[email protected]