Pro Insight: What are Network Signals? Follow
In Pro Insight 2.0, Network Signals are now part of the five results columns.
Network Risk insights are derived from the Ekata Identity Network, our dataset of billions of online transactions used to detect legitimate and anomalous consumer behavior. Network Risk uses machine learning predictions to surface:
- A score of the identity's risk behavior level – HIGH, MEDIUM, or LOW
- 4 behavior categories – activity patterns of identity elements, i.e. Age, Velocity, Volatility, Popualrity
- 12 risk signals – indicating positive or negative behavior across that identity’s transaction history within our Network
Network Risk Signals (By Type of Behavior Pattern)
Network Risk Signals reveal key behavioral fraud and activity patterns of a consumer:
- Velocity indicates the number of times an identity attribute was seen in recent transactions.
- Example - this phone number has been seen in X transactions over the last 90 days.
- Trend - once a fraudster steals an identity, they may try to commit fraud through multiple transactions at the same time before the identity is flagged.
- Volatility indicates the number of times an attribute of an identity has changed over the last 90 days.
- Example - X phone numbers have been associated with this shipping address in the last 30 days.
- Trend - once a fraudster steals an identity, they may use different combinations of identity attributes to commit fraud.
- Popularity indicates the number of merchants where an attribute is seen in recent transactions.
- Example - this phone number has been seen by X number of different merchants in the last 30 days.
- Trend - once a fraudster steals an identity, they may try to commit fraud with multiple merchants at the same time before the identity is flagged.
- Age measures the reliability of an identity element based on its history in Ekata's network
- Example - this address and phone number were first seen together 1 day ago
- Trend - fraudsters typically have a shorter, more fragmented history
Network Signals provide context behind the Network Risk score. Our product and engineering teams tested hundreds of attributes that are within our Identity Network. After this testing, we chose a combination of 147 features based on their proven predictive value. We trained our random forest machine learning model to look across these 147 features, giving equal weight to each input type. Then, our model surfaces the top features based on their predictive power. These top features are the risk signals you find in the panel, and they influence the Risk Indicator to be low, high, or uncertain. The Risk Indicator is a machine learning prediction, derived from the Ekata Identity Network, that provides insight into how risky a digital interaction is based on activity patterns of core identity elements.