Who Feedzai is
Feedzai is a fraud and financial crime company whose founders honed their skills at the European Space Agency. Its RiskOps platform uses AI models in real time against fraud, scams and money laundering across the customer journey, from account opening to payments, with AML transaction monitoring and watchlist screening alongside.
Retail and commercial banks, payment service providers and merchant acquirers use it, and Feedzai IQ adds risk signals learned across its network without raw customer data leaving any institution. That focus on banks and payments is why it is one of the fraud engines our Fraud & risk module connects to.
What it does in your platform
Fraud & risk
Scores card payments, transfers and account activity with Feedzai's real-time models, behavioural and device signals, and the network intelligence of Feedzai IQ. Feedzai explains what drove each decision, and that explanation reaches your analysts with the case.
How the connection works
One connector in the Fraud & risk module sends events to Feedzai's platform as they happen and receives an answer for each in real time. The strategies your risk team sets in Feedzai and the rules in the module work together.
A card payment arrives
The module sends it to Feedzai with what the platform knows: the card, the amount, the merchant, the device and the customer's recent activity.
Feedzai scores it
Its models compare the payment with the customer's normal behaviour and with fraud patterns from the Feedzai IQ network, in milliseconds.
Your strategy applies
The no-code rules your team set in Feedzai turn the score into a recommendation, with an explanation of what drove it.
The module decides
It merges Feedzai's answer with your own rules: allow, ask for a second factor, hold for review or block.
Your team reviews
Held payments land in the case queue in the backoffice with Feedzai's explanation, and analysts work them with the full history on one screen.
Next to other providers
The module can call Feedzai in parallel with another engine, or next to Fingerprint's device intelligence, and merge their signals into one decision. If Feedzai is slow, the decision falls back to your own rules within a set timeout.
Your rules and the case queue belong to the module, so adding another engine next to Feedzai, or replacing it later, does not change your apps, and past decisions stay in your records.
When Feedzai fits best
A strong fit when
- You are a bank, a card issuer or a payment processor with high payment volumes.
- You need fraud decisions in milliseconds, with an explanation for each one.
- You want network intelligence without sharing raw customer data with other institutions.
Also worth a look
- Sardine, SEON or Sift, when your focus is online accounts and payments in a fintech or crypto product.
- Your own models next to Feedzai's, plugged into the module as one more signal.
How we get you live
The contract
We help you get your Feedzai account and contract in place, set up for your products, channels and markets.
The strategies
We set up the rules and thresholds with your risk team in Feedzai, and the matching ones in the module: what is allowed, challenged, held or blocked.
The keys
The credentials for Feedzai's platform go into your platform's secrets and nowhere else.
A full test run
We replay test payments through the whole flow, from scoring to a case in the backoffice, in a test setup agreed with Feedzai, before your first real payment.
