Analyzes How Hashed Identity Elements Are Being Used in Digital Interactions

Ekata 身份网络

Our 身份网络 uses data aggregated from more than 200 million monthly anonymized, real-world queries to predict fraudulent vs. legitimate interactions by analyzing patterns of how identity elements are being used online.

Predictive 风险信号

Produces machine learning predictions based on how identity elements are used in interactions.

Machine Learning

Aggregated Transaction-level Intelligence

Provides insight into cross-border and cross-industry fraud patterns outside of your own data.

Identity Graph

Dynamic Decision Making

Learns with new transactions to provide answers in real time for determining fraud potential.

Unique Data Attributes Built to Improve Your Risk Models

Network Score

Network Score provides insight into activity patterns we observe in our 身份网络. Based on which identity elements are used in a digital interaction, the Network Score will assess the riskiness with a prediction between 0-1.


网络风险 panel is designed to surface the top 12 signals that indicate positive or negative user activity. Signals reveal patterns that help fraud teams identify which customers are good vs. bad.

IP Risk

IP Risk flag assesses the risk of a given IP address in real-time using metadata about the IP address as well as Network data that surfaces how the IP address in question has previously been used.

2,000+ Companies Worldwide Trust The Ekata 身份网络



Knowing what your fraudsters are doing is just as important as knowing who they are. With an evolving landscape of fraud types and tactics, understanding how your fraudsters act will better help you prevent them from committing fraud.



See how the Ekata 身份网络 can improve your risk model. Contact us today.