Ekata, an identify verification solution provider, has announced its latest addition to its identity verification dataset. The new feature, Network Score, uses Machine Learning to better identify good customers and bad customers. Based on activity pattern analysis, Network Score flags potentially risky digital transactions.
“With over 20 years of sourcing identity data from our global data providers, we know that authoritative data isn’t enough,” Rob Eleveld, Ekata CEO, commented in a press release. “Stolen personally identifiable information (PII) and fake digital identities are becoming increasingly prevalent, which makes verifying identity in the digital and card not present (CNP) world harder than ever. Fraudsters can try to impersonate and act the way legitimate users do but they will never match 100 percent of the time; those activity patterns can be powerful signals of fraud.”
Network Score uses Ekata's Identity Network to conduct its analysis. The Identity Network is a global dataset that includes billions of customer transactions. The network allows Ekata to examine behavior with the goal of decreasing false declines and increasing detection of fraud.
Network Score joins Ekata's existing suite of network-related products including Network Risk and IP risk. Because Ekata uses a growing network of transactions and applies machine learning to that network, its tools continue to grow in capability and accuracy over time. Ekata is helping businesses be proactive against fraud across the globe.