Softwr

Cybersecurity · head to head

Feedzai vs ThetaRay

Feedzai logo

Feedzai

Cybersecurity

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

From
On request
Rated
-
Full reviewWebsite
ThetaRay logo

ThetaRay

Cybersecurity

Unsupervised AI transaction monitoring for cross-border and correspondent banking

From
On request
Rated
-
Full reviewWebsite

The short version

  • Each has a real cost: 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.; ThetaRay unsupervised models are harder to justify to an examiner than explicit rules, and some regulators still expect documented threshold logic, which can force you to run both systems.
  • They diverge on capability: Feedzai covers Real-time scoring, ThetaRay covers Unsupervised detection.
  • Prices and features above were last checked on 1 September 2026.

Where they differ

Only the attributes on which Feedzai and ThetaRay actually diverge.

Attributes where Feedzai and ThetaRay differ
AttributeFeedzaiThetaRay
PlatformsWeb, LinuxWeb

Identical on both: starting price (On request), pricing model (quote), free tier (No), user rating (Not yet rated), category (Cybersecurity).

What each one covers

Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Feedzai

  • Real-time scoring
  • Rule and model hybrid
  • Case manager
  • Behavioural biometrics
  • Model explainability
  • Deployment options

Only in ThetaRay

  • Unsupervised detection
  • Cross-border focus
  • Sanctions screening
  • Alert triage
  • Customer risk scoring
  • Cloud native

What people use each for

The jobs each tool is most often brought in to do.

Feedzai

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

ThetaRay

  • A correspondent bank that cannot see the ultimate originator and needs behavioural signals rather than counterparty listsnot Feedzai
  • A cross-border payments fintech whose rules engine produces more alerts than its compliance team can clearnot Feedzai
  • A bank under a regulatory consent order needing demonstrable improvement in detection within a fixed periodnot Feedzai
  • A payment institution entering a high-risk corridor where existing thresholds were calibrated on domestic trafficnot Feedzai

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

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.

ThetaRay

  • Unsupervised models are harder to justify to an examiner than explicit rules, and some regulators still expect documented threshold logic, which can force you to run both systems.
  • The alert reduction claim depends heavily on your data, so a parallel run is essential and adds months and cost before you can decommission the incumbent.
  • Coverage is strongest in cross-border and correspondent flows; institutions whose risk is domestic retail fraud will find the fit weaker than a general-purpose monitoring platform.
  • It is a smaller vendor than the incumbents, so integration connectors into legacy core banking systems are often bespoke work rather than a supported adapter.
  • Model retraining and tuning are vendor-led, which means changing detection behaviour is a support conversation rather than something your own analysts can do that afternoon.

Pricing, plan by plan

Feedzai

On request
  • Feedzai Financial Crime Platform$undefined/year
    • Priced by transaction volume with annual minimum commitment
    • Modules for fraud, AML and account opening licensed separately
    • Cloud, private cloud and on-premises deployment

ThetaRay

On request
  • ThetaRay Sonar$undefined/year
    • Priced by monitored transaction volume and number of monitored entities
    • SaaS on Azure with regional data residency options
    • Parallel run and model tuning included in onboarding

Which should you pick?

Choose Feedzai if

  • You need real-time scoring.
  • You work on Web, Linux.
  • You also want rule and model hybrid.
Feedzai review

Choose ThetaRay if

  • You need unsupervised detection.
  • You also want cross-border focus.
ThetaRay review

Questions people ask

Is Feedzai or ThetaRay better?
Neither clearly leads. Feedzai starts at On request and ThetaRay at On request, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Feedzai or ThetaRay?
Feedzai starts at On request and ThetaRay at On request.
Does Feedzai or ThetaRay run on more platforms?
Feedzai runs on Web, Linux. ThetaRay runs on Web.
What is Feedzai best used for?
Feedzai is most often used 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. Of those, a bank joining an instant payments scheme where transfers are irrevocable and post-hoc recovery is impossible and a card issuer whose existing rules engine cannot be changed without a release, so fraud waves run for days are not what ThetaRay is typically brought in for.
What can Feedzai do that ThetaRay cannot?
Feedzai covers Real-time scoring, Rule and model hybrid, Case manager, Behavioural biometrics. ThetaRay covers Unsupervised detection, Cross-border focus, Sanctions screening, Alert triage.

Answered from the vendors’ own pages

Feedzai: 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.

ThetaRay: Does it replace a rules engine entirely?

Rarely on day one. Most institutions run it alongside existing rules during a parallel period, and some keep specific regulator-mandated rules permanently.

Feedzai: 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.

ThetaRay: Where is the data processed?

SaaS runs on Microsoft Azure with regional deployment options, which is the mechanism for meeting data residency conditions in regulated markets.

Feedzai: How fast are decisions?

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

ThetaRay: Is sanctions screening included?

Screening is available on the same platform but licensed as part of the commercial package rather than bundled by default. Confirm it is in your quote.

Share

Related pages

More on Feedzai

More on ThetaRay

Keep looking

Other head to heads