Feedzai

Real-time transaction fraud and financial crime detection for banks and payment processors

As of 1 September 2026, Feedzai's pricing is not published; the vendor quotes on request. Machine learning fraud scoring that sits in the authorisation path for card and account-to-account payments. Softwr lists it under Cybersecurity. Feedzai is available on Web, Linux.

Visit siteVisit Feedzai

Overview

What Feedzai does

Feedzai scores payments, account openings and account changes for fraud and money laundering risk in real time. It ingests transaction streams, enriches them with device, behavioural and network signals, applies both rules and supervised models, and returns a decision inside the authorisation window. It is deployed by card issuers, acquirers, real-time payment schemes and merchants who need decisions in single-digit milliseconds. The distinguishing property is that Feedzai is built to be operated by the bank fraud team, not only by data scientists. It exposes a case manager, rule authoring, model explainability output and champion-challenger testing so a fraud analyst can change policy without a deployment cycle. That matters commercially because fraud patterns move faster than a machine learning release schedule, and a platform that requires an engineering ticket for every rule change loses money in the interval. Buyers are banks and processors in markets with instant payments, where the irrevocability of a real-time transfer removes the chargeback safety net. The trade-off is cost and integration depth. Feedzai sits in the critical payment path, so the deployment is a core banking integration with all that implies for testing and change control, and it is priced for institutions moving hundreds of millions of transactions.

What people use it for

A bank joining an instant payments scheme where transfers are irrevocable and post-hoc recovery is impossible
A card issuer whose existing rules engine cannot be changed without a release, so fraud waves run for days
An acquirer needing per-merchant risk models rather than one portfolio-wide model
A bank required by its regulator to explain automated declines to customers, which rules out opaque scoring

Where it falls short

Concrete and checkable, so you can decide whether any of them matter to you. This is the half of a review a vendor will not write about Feedzai.

Pricing is per transaction with an annual minimum, so a bank with seasonal or growing volume commits to a floor it may not use and pays overage above the band.
It sits in the authorisation path, which makes every upgrade a change-controlled event with rollback plans, and the operational burden falls on the bank rather than the vendor.
Out of the box models need months of the customer own labelled fraud history before they beat the rules they replace, so the value case starts late.
AML and fraud are licensed as separate modules, so institutions expecting one platform fee find the transaction monitoring capability is a second line item.
The buyer profile is large institutions, so smaller banks and fintechs face minimums that make per-transaction economics unattractive below significant scale.

Cross-shopped

What people choose instead of Feedzai

Each pairing was judged by two reviewers asking whether a buyer would genuinely weigh the two against each other. The ones that failed were deleted rather than published.

Feedzaivs
Unit21
Unit21: Lower entry point and far easier for a small risk team to operate, with rule authoring aimed at fintechs rather than tier one banks
Feedzaivs
ThetaRay
ThetaRay: Better fit when the priority is unsupervised detection of unknown patterns in correspondent banking rather than card fraud

Pricing

What Feedzai costs

Taken from the vendor's own pricing page. Prices move, so check before you buy.

Feedzai Financial Crime Platform

On request

Priced by transaction volume with annual minimum commitment
Modules for fraud, AML and account opening licensed separately
Cloud, private cloud and on-premises deployment
Model development services quoted separately

Capabilities

Features

Real-time scoring
Sub-hundred millisecond decisions inside the payment authorisation window
Rule and model hybrid
Analyst-authored rules run alongside supervised models, with champion-challenger comparison
Case manager
Investigator workflow with alert queues, linked entities and SAR preparation
Behavioural biometrics
Typing, gesture and navigation signals used as fraud features on digital channels
Model explainability
Reason codes for each decision, needed where regulators require adverse action explanations
Deployment options
Feedzai Cloud, private cloud or on-premises for institutions that cannot export transaction data

Answered, with sources

Questions people ask

Each answer names the page it came from, so you can check it rather than take our word for it.

Can Feedzai run on-premises?

Yes. On-premises and private cloud deployments are supported, which is why it appears in markets where transaction data cannot legally leave the country.

Does it cover AML as well as fraud?

It does, but transaction monitoring is a separately licensed module. Assume two line items if you want both.

How fast are decisions?

Designed for the authorisation window, typically tens of milliseconds. This is the constraint that rules out batch scoring architectures.

Keep looking

Where to go from Feedzai

Best Cybersecurity software for

Compare Feedzai with

Other Cybersecurity software

Unit21
No-code fraud and AML risk operations platform for fintechs and neobanks
Pricing on request10 researched notes
ThetaRay
Unsupervised AI transaction monitoring for cross-border and correspondent banking
Pricing on request10 researched notes
Featurespace ARIC Risk Hub
Adaptive behavioural analytics for payment fraud and financial crime
Pricing on request10 researched notes
NICE Actimize
Financial crime, risk and compliance suite for regulated institutions
Pricing on request10 researched notes
Quantexa
Entity resolution and network analytics for financial crime investigation
Pricing on request10 researched notes
Sardine
Device intelligence and behaviour biometrics for fraud and compliance
Pricing on request10 researched notes
Silent Eight
AI adjudication of sanctions screening and AML alerts
Pricing on request10 researched notes
Transmit Security
Customer identity platform built around passwordless and fraud signals
Pricing on request11 researched notes
Fenergo
Client lifecycle management and KYC onboarding for regulated financial institutions
Pricing on request10 researched notes
Socure
Predictive identity verification and fraud scoring for the US market
Pricing on request11 researched notes
Sumsub
Identity verification and AML screening priced per verification
From $1.35/verification10 researched notes
iDenfy
Identity verification and AML screening bundled into a single per-verification price
11 researched notes
BeyondTrust
Privileged access management, endpoint privilege management and secure remote access
Pricing on request11 researched notes
Bitdefender VPN
Consumer VPN sold by Bitdefender that runs on network infrastructure licensed from a third party rather than its own.
14 researched notes
Burp Suite
The leading toolkit for web security testing
Free, then $449/yr11 researched notes
Check Point Software
AI Transforms the Network. We Transform the Firewall.
Pricing on request9 researched notes
Cybereason Defense Platform
AI-driven endpoint protection and detection
From $50/yr11 researched notes
Darktrace
Autonomous threat detection and response
From $20,000/yr8 researched notes

Softwr does not host reviews and shows no star rating for Feedzai, because a rating we did not collect is not ours to publish. What is here is the pricing and platform detail from the vendor’s own pages, limitations we could state concretely, and alternatives a reviewer confirmed people weigh against it. Tell us if any of it is wrong.

Best Cybersecurity software alternatives

View all Cybersecurity software