Fraud Detection & Transaction Risk
A

Acoru

Acoru sells scam and money mule detection to banks and other financial institutions. Chief executive Pablo de la Riva Ferrezuelo and David Morán founded it in Madrid in December 2023, and the founders previously built Revelock, which Feedzai bought. Adara Ventures and Athos Capital backed its €4 million seed round, and 33N Ventures led a €10 million Series A in 2025.

The Continuous Account Intelligence Platform joins account, transaction, session and device data from digital banking, call centers, payment systems and card networks. It keeps each account classified as regular, victim or mule as new events arrive, so a bank can catch a customer being coached into an authorized push payment before the money leaves, or a mule account as it receives funds. Banks call Acoru at control points such as login, payee setup and payment, or take alerts when linked accounts change risk.

Inspector gives analysts dashboards, alerts and reports, and Flows is a no code canvas for building attributes and metrics. AI Studio lets teams build and test models on the bank's own data, including Acoru's Large Account Model, and the AI Workforce prepares cases and drafts rule changes for people to approve.

Banks buy Scam Prediction and Mule Classification alongside their existing monitoring, or Holistic Fraud Prevention as a fuller replacement. Consortium Manager lets member banks exchange tokenized intelligence without pooling records. Acoru runs on premises, in a private cloud or in a hybrid setup and has ISO/IEC 27001:2022 certification and SOC 2 Type II reports.

Last VerifiedNovember 20, 2026
Compare Acoru with other vendors
Founded
2023
Headquarters
Madrid, Spain
Categories
fraud-and-transaction-risk, aml-kyc-financial-crime
Assessment

Capability Axes

Capability grades

15 of 15 axes rated · 12 graded A or B

AI Capability
AI Centrality
AA on AI CentralityThe artificial intelligence is the product. Remove the models and there is nothing left to sell.
Vendor Published

Models are the product. They build structured frames from account, session and transaction data, learn how each account normally behaves and keep reclassifying accounts and counterparties as regular, victim or mule as events change. AI Studio runs conventional machine learning beside transformer models such as Acoru's Large Account Model, and the AI Workforce applies the same account intelligence to monitoring and case building. Without the models the platform would have nothing to score at login, payee creation or payment.

Autonomy and Oversight Model
AA on Autonomy and Oversight ModelWhat the system runs alone, what constrains it, and how a person checks it are all published: modes, thresholds, sampling or audit controls, and the route a case takes to human review.
Vendor Published

The bank sets the policy that decides which controls fire on their own at authentication, payee setup and payment, and Acoru supplies the updated classification and its evidence at each point. Every intervention carries reason codes and records the logic behind it. The AI Workforce gathers the details of a case while analysts make the call, and any rule or model change it drafts is versioned and needs human approval before it reaches production.

Model Risk Management and Transparency
BB on Model Risk Management and TransparencyReal transparency mechanisms are published, such as per alert explainability, confidence scoring or split testing, without the validation package or supervisory mapping behind them.
Vendor Published

Every classification carries the behavioral sequence and rule triggers that produced it, and teams can trace the model and policy behind each execution. AI Studio trains on frames built from the bank's transactions, behavior and account relationships, and compares a proposed model with the live one on production data through simulation and backtesting. Validation therefore happens in each bank's own deployment, and a benchmark of the models across institutions has not been published.

Operational and Outcome Evidence
CC on Operational and Outcome EvidenceUnnamed case studies, customer logos, or claims without numbers. Prestige is not measurement: the caliber of the client list describes the buyer rather than the product, and coverage statistics are not adoption statistics.
Vendor Published

Acoru says it works with banks and financial institutions of all sizes and reported revenue growth at its 2025 Series A, and investor Adara Ventures describes expansion across Europe and the Americas. Datos Insights included it in its Fraud and AML Fintech Spotlight report.

A named bank with a measured result on scam losses, mule detection or investigation time has not been shared, and the worked examples on the site illustrate the sequence from early account events to a scam payment rather than a customer's figures.

AI Safety and Data Stewardship
BB on AI Safety and Data StewardshipA categorical stewardship commitment is published without the retention schedule or the engineering detail behind it.
Vendor Published

AI Studio trains models on the bank's data inside the bank's infrastructure, so one institution's records do not leave for a shared training set. Learning across banks happens only through Consortium Manager, as distributed learning under policies each member configures, with scoped and tokenized intelligence moving between nodes and no intermediate storage. Retention periods for the AI components and terms for any outside assistant model are left to the contract.

Regulatory and Compliance
GLBA and Data Privacy Posture
BB on GLBA and Data Privacy PostureA substantive privacy document that reaches the product itself, short of the subprocessor list or the full data handling detail.
Vendor Published

Account and session data stay inside the bank's own environment, and personal information remains on premises even when banks collaborate. Consortium members share only policy approved intelligence, using derived responses without identifiers, cryptographic matching or encrypted computation, and there is no shared data store between member nodes. The privacy notice from AntSwarm Security Intelligence Network, Acoru's corporate name, covers website visitors, while the bank controls what leaves its environment.

Security Certifications and Trust Center
BB on Security Certifications and Trust CenterA recognized certification named in the vendor’s own material without the artifact, or with a scope or renewal question the buyer has to raise.
Vendor Published

Acoru's Vanta trust center lists ISO/IEC 27001:2022 certification and SOC 2 Type I and Type II reports, with the certificate, the reports and the 2026 ISO audit report released on request. Its public control list covers key management, source code access, backup, security testing and the separation of test and production. Because the product can run inside the bank's own environment, much of the hosting security there is the bank's.

Regulatory Status and Licensure
BB on Regulatory Status and LicensureThe regulatory position is clearly stated and appropriate to the product, with part of the verification left to the buyer.
Vendor Published

Acoru supplies technology to banks rather than carrying out regulated payments or lending itself. It frames its controls around the rules its customers face: the UK Payment Systems Regulator's PS23/4 reimbursement regime for authorized push payment fraud, PSD3, Nacha's fraud monitoring rules and Regulation E, with DORA on its compliance list. Signed event and policy trails export for internal and supervisory review, and reimbursement and payment decisions stay with the bank.

AI Governance and Bias Disclosure
BB on AI Governance and Bias DisclosureAn independent demographic evaluation the vendor has submitted to, such as the NIST face evaluation class, or a governance framework with named process behind it.
Vendor Published

Model change in production follows a named process. AI Studio shows which models are live, the policies that use them and what those policies produce, AI Workforce suggestions arrive as versioned drafts that need human approval, and signed decision records tie each outcome to its policy and evidence. Error rates for victim and mule classifications across customer groups have not been released.

AI Liability and Recourse
CC on AI Liability and RecourseMechanisms that enable challenge, such as audit trails and source traceability, with nothing standing behind the output and no route for the person affected.
Vendor Published

Each held payment or flagged account traces back to its reason codes, the model, the events and the policy behind it, and analysts use that record to sustain or lift an intervention. Reimbursement under schemes such as PS23/4 stays the bank's decision and cost. No indemnity, guarantee or financial commitment from Acoru stands behind a missed scam or a wrong classification, and product terms beyond the website terms have not been made public.

Integration and Deployment
Model Supply Chain Disclosure
BB on Model Supply Chain DisclosureSubstantial partial disclosure, or a chain that is structurally short: an explicit in house build, on premise deployment, per customer instances, or zero retention at the model layer.
Vendor Published

The Large Account Model is Acoru's own transformer, offered in AI Studio beside conventional machine learning, and banks can build further models on their own normalized data inside the platform. That keeps the detection chain short and in house. The AI Assistant and AI Workforce run on the same evidence paths, but the language models behind them and their providers are not named.

Core Systems and Integration Depth
BB on Core Systems and Integration DepthNamed systems or a documented public API, with the depth or the production evidence left open.
Vendor Published

Acoru takes data in through APIs, streams, queues and plug in connectors, from account records to session events such as a new payee, and correlates signals from digital banking, call centers, payment systems and card networks. Scores and alerts go out to the bank's case management or security monitoring tools, or come back as a response at a single control point. The connectors are not named against particular core banking or fraud vendors.

Deployment Model and Data Residency
AA on Deployment Model and Data ResidencyOn premise or hybrid deployment is offered and documented, alongside where data rests.
Vendor Published

Banks can run Acoru on premises, in their own private cloud or in a hybrid setup, choose who operates the infrastructure and use one tenant or several. The data and scoring pipeline sits beside the bank's channel and monitoring stack inside its environment. Consortium Manager runs as a separate layer in which each participant connects through its own node and no shared database holds records between them.

Commercial
Commercial Transparency
CC on Commercial TransparencyNo price is published and engagement runs through a demo form, which is the norm in this index.
Vendor Published

Acoru sells through demonstrations and its enterprise sales team, and a bank chooses between two packages. Scam Prediction and Mule Classification works beside an existing fraud and monitoring stack, while Holistic Fraud Prevention replaces more of it, and Consortium Manager is an optional add on that can also run as its own network layer. Price, billing unit and implementation cost for each combination are set in the agreement.

Institution and Segment Coverage
BB on Institution and Segment CoverageNamed segments with dedicated material behind part of the coverage.
Vendor Published

Banks are the buyers, with packages for two situations: fraud teams that already run transaction monitoring and online fraud tools and want scam and mule detection on top, and institutions replacing those tools with one platform covering funding, login and payment. Financial crime teams that want to share intelligence with peers get Consortium Manager, and a separate page addresses US institutions. Which banks use each package has not been disclosed.

Alternatives to Acoru

Other products that do the same kind of work as Acoru, and what each one does.

Cybera sells banks, crypto platforms and cyber insurers two products aimed at authorized payment scams.

Outseer sells fraud prevention to banks, card issuers and other financial institutions, protecting digital banking sessions and 3-D Secure card payments.

Transmit Security sells Mosaic, a cloud platform that combines customer identity, fraud detection and identity verification for banks, insurers and other large consumer brands.

Charm Security sells scam and social engineering defense to banks, fintechs, payment providers and credit unions.

Clari5 sells a real time platform that brings enterprise fraud management, anti money laundering, compliance and investigations together for banks.

T-NEX Fraud Detection is a transaction monitoring and case investigation module for fraud and anti money laundering teams at regulated institutions.

Commercial

Pricing

Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.

Entry Price Pricing Basis Data Protection Terms Implementation Source
Quoted through Acoru's enterprise sales team.
Banks license one of two fraud packages, with Consortium Manager as an optional add on. Data terms are set in each bank's agreement, and the platform can run inside the bank's own environment. Implementation cost depends on the package and the deployment model chosen. Vendor Published

Acoru sells Scam Prediction and Mule Classification to banks that keep their existing fraud stack and Holistic Fraud Prevention to those replacing it. Consortium Manager can be added or deployed on its own. The price depends on the services licensed, the deployment model and the agreement with Acoru.

Contact us

Found a vendor we missed? Have feedback on the index? We’d love to hear from you.

AI FinTech Index

The AI FinTech Index is an independent index that tracks changes to AI vendors in financial services. It holds 797 vendors across banking, lending, insurance, wealth, capital markets and financial crime compliance, each graded on the same 15 capability axes from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 21, 2026
The AI FinTech Index is an editorial reference, not a regulatory body. Vendor data is verified against published sources and public regulatory filings. Figures labeled “Estimated” have not been confirmed by the vendor. See the Methodology page for evaluation standards and limitations.
© 2026 AI FinTech Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746