Incognia has launched Real-Time Scam Prevention, using location-based links between payment senders and recipients to help banks detect scams.
Cross-device risk intelligence provider Incognia has introduced Real-Time Scam Prevention, an AI-powered solution designed to help financial institutions detect and prevent payment scams, including authorised payment fraud and social engineering schemes. The solution combines Incognia’s Physical Social Graph with additional risk signals. Authorised payment scams are difficult to detect because the customer making the payment may be using a legitimate account, device, and credentials, and traditional fraud controls that verify the person initiating a transaction may miss signs that the customer is being manipulated. According to the US Federal Trade Commission, consumers reported losing USD 3.5 billion to impersonation scams in 2025, nearly triple the amount reported in 2020.
Relationships between senders and recipients
The Physical Social Graph is powered by Incognia’s patented Trusted Locations technology, which uses persistent, apartment-level indoor location data to identify real-world connections between payment senders and recipients that transaction data alone may not reveal. Rather than relying on a customer’s location at the moment of a transaction, the system builds location patterns from where users regularly spend time and compares the historical patterns of sender and recipient to identify relationships that may indicate risk.
According to Incognia, in an analysis of transactions from a major financial institution, the Physical Social Graph alone identified around 70% of scam transactions in the dataset. André Ferraz, Co-Founder and CEO of Incognia, stated that banks have become effective at confirming whether the person making a payment is legitimate, but in a scam, the legitimate customer is often the one sending the money. According to Ferraz, the key question becomes who the money is going to and whether that relationship makes sense.
Combining multiple risk signals
Incognia’s AI model combines the Physical Social Graph with mule account detection, active call detection, remote access tool detection, device integrity checks, and location spoofing detection to assess payment risk in real time. Banks use these assessments alongside their own data and policies to decide how to respond. The solution also links payment activity and real-world relationships across participating financial institutions, helping to uncover suspicious networks that individual banks may not detect on their own.
Alan Gomes, CTO of Incognia, stated that two people living in the same building may have no real-world relationship, while two people in different cities may know each other well, so distance alone is not a reliable indicator. According to Gomes, apartment-level indoor location data identifies patterns and connections over time, providing context that IP addresses or GPS coordinates alone cannot. The launch reflects a shift in scam prevention from verifying the payer towards assessing whether the relationship between payer and payee is genuine.
