Skip to content

AI Transaction Monitoring: How a Transaction Ontology Gives Banking AI the Context Behind Every Payment

AI Transaction Monitoring

Key Takeaways

  • AI transaction monitoring scores payments without the relationships behind them, so alerts are noisy and hard to explain. Shared owners, merchant hierarchies and product rules sit in KYC files, acquirer data and product terms that the monitoring model never reads.
  • A transaction ontology links each payment to its accounts, parties, beneficial owners, merchants, counterparties, products and rules. Public standards such as FIBO, the Legal Entity Identifier and ISO 20022 supply much of the shared vocabulary.
  • Network context finds what single-account scoring misses. In the BIS Innovation Hub's Project Hertha, published in June 2025, payment system analytics helped banks find 12% more illicit accounts and improved detection of previously unseen behavior by 26%.
  • Examiners need to retrace why an alert was raised or closed. SR 26-2, issued in April 2026, leaves generative and agentic AI models to each bank's own governance, so the trace has to be built into the system.
  • Start with one alert type on one product line. A first release of 10 to 20 questions, tested against cases the bank has already closed, usually takes 8 to 12 weeks.

QUICK ANSWER

What does a transaction ontology add to AI transaction monitoring? AI transaction monitoring uses rules, machine learning and increasingly AI agents to flag payments that may involve money laundering or fraud. A transaction ontology adds the context those models score without: who owns and controls each account, what a merchant really is, which product rules apply and how the parties connect. With that context, the system groups related activity before it alerts, and each alert carries a rationale an investigator and an examiner can retrace.

Most banks already run transaction monitoring, and many are adding machine learning or AI agents on top of it. The complaint from compliance teams stays the same: too many alerts close as false positives, and the ones that matter are hard to explain. The facts an investigator needs usually exist somewhere in the bank, spread across systems the monitoring model doesn't read.

Mactores has built data platforms and AI agents on AWS since 2008, much of it for regulated companies, including a real-time MBS pricing platform that records its own lineage and a payments platform cut over without an audit incident. This guide draws on that work and on the delivery method we use for transaction ontologies.

What Is AI Transaction Monitoring?

AI transaction monitoring is the use of machine learning, and increasingly AI agents, to review payments and account activity for signs of money laundering, fraud or sanctions evasion, alongside or in place of fixed rules. AML transaction monitoring is its regulatory core: a bank has to detect suspicious activity and, under 31 CFR 1020.320, generally file a suspicious activity report within 30 calendar days of first detecting it.

It's already widespread. In the Cambridge Centre for Alternative Finance's 2026 global survey of 628 organizations in 151 jurisdictions, AML/CFT and KYC was among the most widely adopted AI uses in risk and compliance, cited by 52% of the industry firms surveyed, behind fraud detection at 57%. Regulators are encouraging it too. FinCEN's proposed AML/CFT program rule of April 2026 encourages institutions to evaluate whether new technology might help and names machine learning and generative AI as examples.

Approach

What it looks at

What it can explain

Rules and thresholds

One account's activity against fixed scenarios

Which scenario fired and which threshold was crossed

Machine learning scoring

Patterns across many features, usually per account or customer

A risk score and the features that moved it

AI agents on the monitoring data

Whatever the agent can retrieve from the systems it's connected to

A written rationale, as good as the context it found

AI with a transaction ontology

The payment plus its owners, merchants, counterparties, products and rules

The parties, links, rule and sources behind the alert

Why Do Transaction Monitoring Models Flag the Wrong Things and Struggle to Explain Why?

Because they score each transaction with the data in the monitoring feed, and the facts that decide what a payment means sit somewhere else. Who controls an account is in KYC and beneficial ownership records. What a merchant really sells is in acquirer data. Which volumes are normal depends on the product terms. A model that can't see those links raises alerts on activity that's routine for the customer and misses activity spread across accounts that look unrelated.

Each system also names the same thing its own way. Core banking knows an account holder, the CRM knows a party under another ID, and the beneficial ownership file knows the person behind both. In our context ontology for financial services work, the failures that show up at almost every institution start there: AML alerts close as unrelated when one person sits behind several accounts, fraud agents misjudge merchants whose descriptors and category codes disagree, and alert rationales fall apart in review because nothing recorded which data and rules produced them.

What goes wrong with the alert

The fact the model didn't have

Where that fact usually lives

A cash-heavy business alerts every week

Its account type carries higher expected cash volumes

Product terms and the KYC profile

Deposits split across several accounts never alert

One person owns or controls all of the account holders

Beneficial ownership records collected at account opening

A card merchant is scored as low risk

It has changed what it sells while keeping its category code

Acquirer data and merchant onboarding files

An outbound wire to a known party is missed

The beneficiary is linked to a customer the bank exited

Payment messages and customer exit records

A closed alert can't be defended in review

Which data, rule and threshold version led to the decision

Nowhere, unless the system records it

Relationships across accounts are where the extra detection comes from. In Project Hertha, the BIS Innovation Hub and the Bank of England tested analytics on payment system data covering 1.8 million synthetic accounts and 308 million transactions. Banks and payment providers using it found 12% more illicit accounts than they would have alone, with a 26% improvement when the criminal behavior was a pattern they hadn't seen before. The project framed the analytics as a supplement to each bank's own monitoring and named explainable AI among the things that make it effective.

Explanation is the other half of the problem. In the same Cambridge survey, 79% of the 130 regulators who took part rated explainability as critical or important to their regulatory objectives. An alert that can only say "unusual amount" gives an investigator nowhere to start and an examiner nothing to test.

What a Transaction Ontology Captures: Accounts, Parties, Merchants, Counterparties, Products, Rules

A transaction ontology is a governed, machine-readable model of each payment and everything that gives it meaning. It names the things a bank deals with, how they connect and which rules apply, and it ties every local identifier for a customer, account or merchant to one shared record. Filled in with the bank's actual records, it becomes a financial knowledge graph that monitoring systems and agents can follow from one alert to every related party.

What it captures

What the monitoring feed usually has

What the ontology adds

A standard to start from

Accounts

An account number, balance and transaction history

The product, owners, signatories, limits and the ledger it posts to

FIBO clients and accounts

Parties and beneficial owners

A customer ID per system

One party across core, CRM and KYC, plus who owns or controls each legal entity

FIBO ownership and control, the LEI

Merchants

A card descriptor and a category code

One merchant identity behind its descriptors, merchant IDs and category history

ISO 18245 merchant category codes

Counterparties

Free-text name and account fields in a payment message

The other side of a wire, ACH entry or trade, resolved to a known party where possible

ISO 20022 fields, the LEI

Products and channels

A product code

The terms that change what a payment means: card, ACH, wire, RTP, FedNow, branch or mobile

FIBO financial products and services

Rules

Scenario thresholds inside the monitoring engine

Monitoring, sanctions and access rules written as checks, each with an owner and a version

Your own policies, written in SHACL

The ontology connects the nouns of banking, such as customers, accounts, payments and cases, with its verbs, such as hold, escalate, reverse and report. It also keeps provenance: which source system supplied each fact, when it changed and which rule relied on it. That's what separates it from a data catalog, and it's the idea of an ontology in AI applied to payments.

Much of the vocabulary already exists. FIBO, the Financial Industry Business Ontology, is maintained by the EDM Council through an open community process, standardized by the Object Management Group and published with formal updates every quarter, most recently in its third-quarter 2026 release on October 20. Its Business Entities domain includes modules for ownership parties, control parties and corporate ownership, and its Financial Business and Commerce domain covers clients, accounts and financial products. For legal entities on either side of a payment, the Legal Entity Identifier system reached 3.19 million active LEIs at the end of the third quarter of 2026.

What no standard holds is the bank's own meaning: its products, its scenarios, its thresholds and the definition of a related party its BSA officer will sign. Those come from the people who own them. For US banks, the beneficial ownership facts usually come from the customer due diligence rule at 31 CFR 1010.230, which has a bank identify, when an account is opened, each individual who owns 25 percent or more of a legal entity customer and one individual with significant responsibility to control it.

"In an ontology in AI, a business rule is attached to the thing it governs, so the agent meets it whenever it touches a payment hold rather than whenever a prompt happens to mention AML."
Gautham B, Forward-Deployed Engineer, Data Engineering practice, Mactores
 

The ontology doesn't replace core banking, the card processor, the monitoring engine or the warehouse. On the open-source Context Ontology Accelerator, it reads those systems in place through a virtual knowledge graph and serves the result to agents through an MCP server, inside the bank's own AWS account.

What a transaction ontology captures: one payment linked to the account, the party and its beneficial owner, the merchant, the counterparty, the product and channel, the monitoring rule and the alert and case, with the public standards each starts from: FIBO, the LEI, ISO 20022 and ISO 18245

How Context Changes an AML or Fraud Alert

It changes what the alert is about. Without context, the system alerts on transactions. With a transaction ontology, the alert is about a set of related parties, the rule they may have broken and the evidence for it.

Take structuring, one of the oldest patterns in AML: cash deposits kept just under the $10,000 currency transaction report threshold of 31 CFR 1010.311, spread across branches and accounts so no single deposit triggers the report. A monitoring system that scores each account alone sees deposits on accounts held by different small businesses. Each may sit below the scenario threshold, or each may raise its own alert. Either way, the investigator starts by pulling the core ledger, the CRM, the KYC files and past cases into one place, and the alert's stated reason is an amount near a threshold.

With a transaction ontology, the same deposits resolve to their legal entity customers, and the beneficial ownership records the bank collected at account opening show whether one person owns or controls them. The product terms show whether any account is a cash-intensive business with its own expected volumes, and earlier alerts and case outcomes for the same parties come linked. The aggregation rule the BSA officer signed then runs over the whole group, and the investigator receives one alert naming the parties, the ownership link, the rule and the sources behind each.

For one structuring alert

Without context

With a transaction ontology

What raises the alert

Each account's deposits against a threshold

The related parties' deposits, aggregated under the signed rule

Where the investigator starts

Pulling ledger, CRM, KYC and case data by hand

A case with the parties, links and history already assembled

What the rationale says

Amount near a threshold

Who is connected, how, under which rule, from which sources

What an examiner can retrace

The alert and the analyst's notes

Every fact, rule version and access decision behind the outcome

The decision stays with the investigator. If the activity is reported, the SAR narrative starts from that rationale, and the 30-day clock in 31 CFR 1020.320 is easier to meet when the evidence is already assembled. The same rule set also protects what the bank must keep quiet: a SAR and any information that would reveal one are confidential, so the ontology's access policies keep SAR-related data out of reach for every role and agent that shouldn't see it, which is the core of agentic AI governance in a bank.

Fraud alerts change the same way. A card fraud model that knows one merchant identity behind its descriptors, merchant IDs and category history can tell a merchant that changed its business from one that was always risky. ACH monitoring needs the history of originators and receivers. Nacha's 2026 risk management rules, which took effect in phases on March 20 and June 19, 2026, require risk-based processes reasonably intended to identify ACH entries initiated due to fraud, and receiving banks must look for fraudulent credits. Instant payments on RTP and FedNow add urgency, because the context has to be there before the money moves.

One structuring alert before and after a transaction ontology: without context, cash deposits just under $10,000 on separate business accounts are scored one account at a time; with the ontology, the accounts resolve to one beneficial owner, the signed aggregation rule runs over the group and the investigator receives one alert with the parties, links, rule and sources

Making Each Alert Traceable for Examiners

Store the explanation with the alert. Each alert, and each step an agent takes on it, should keep the data it read, the definitions and rules it applied, what each role was allowed to see and the ontology version in force, so an examiner can replay the conclusion months later.

Supervisory guidance now makes that the bank's job. On April 17, 2026, the Federal Reserve, OCC and FDIC issued SR 26-2, which supersedes SR 11-7 and SR 21-8, the 2021 interagency statement on model risk management for systems supporting BSA/AML compliance. Its definition of a model leaves out deterministic rule-based processes with no statistical theory behind them, and a footnote places generative and agentic AI models outside its scope, leaving their controls to each bank's own risk management and governance. A monitoring stack can therefore hold three kinds of component under three sets of expectations: threshold rules, machine learning scores and agents. A trace that covers all three is the simplest way to answer an examiner about any of them.

We've built this kind of evidence into regulated systems before. On the real-time MBS pricing platform we delivered for a capital markets customer, every signal, model invocation and trading decision is traced and logged as the system runs, so audit evidence aligned to FFIEC, SEC and FINRA expectations is captured at the moment of decision. The same principle runs through our financial services data modernization work, where the evidence an examiner will ask for is generated while the system is being built.

"Encryption, masking, fine-grained access, lineage and audit logs get created as data moves, so the evidence exists before an auditor asks."
Ram Tiwari, Forward-Deployed Engineer, Spark Data Engineer, Mactores

What an examiner asks about an alert

Where the answer comes from

"Why was this alert closed without escalation?"

The stored rationale: the parties resolved, the links followed, the rule and threshold applied

"Which definition of a related party applied that month?"

The definition's version history and the steward who approved each change

"Could the analyst or the agent see SAR-related information?"

Entitlement test results for each role and the query log

"Which sources did the rationale rely on, and how fresh were they?"

Source lineage and refresh times recorded with the answer

"Which ontology release produced this alert?"

The release history linked to the alert trace

Recording those decisions as they happen, with the sources and rules behind each one, is what a context graph is for. The same habit carries into cutovers: on the branded-payments platform we moved to AWS, agents instrumented the parallel run, our engineers sequenced the cutover by risk, and production sign-off came with zero audit incidents.

Where to Start: One Alert Type, One Product Line

Pick the alert type that wastes the most investigator time on one product line, write down the 10 to 20 questions investigators ask about it, and build only the ontology those questions need. We don't ask a bank to model the whole enterprise before proving value.

Alert type

Product line

Why it makes a good first scope

Cash structuring and aggregation

Small-business deposit accounts

Beneficial ownership links decide most outcomes, and the rule is easy to state and sign

ACH credit-push fraud

Business ACH origination or receipt

Nacha's 2026 rules already require risk-based monitoring, and originator history is the missing context

Card fraud and disputes

Consumer cards

One merchant identity across descriptors and category history fixes a large share of misreads

Rapid movement of funds

Instant payments on RTP or FedNow

There's no recall window, so context has to arrive before release

From there, our delivery runs in five phases, each closed by a signed exit: frame the questions, resolve parties and sources, agree meaning and rules with the risk and compliance owners, test against known outcomes, then go live in stages under parallel running. A first release usually takes 8 to 12 weeks and covers a few source systems. Testing uses questions whose answers are already settled, such as cases the bank has closed, and every role is checked against its entitlements, including refusals for SAR-related data and information barriers.

What derails a first release

What we'd do instead

Modeling every product and alert type before proving one

Scope to one alert type and one product line, and let the second release reuse the parties and owners the first one resolved

Party and account data that disagree across systems

Make party resolution the first phase, with match rules the data owners sign

Rules the business has never written down

Hold definition sessions with the BSA officer and fraud lead before encoding anything

Agents allowed to close alerts or move money

Let agents assemble and draft, and keep every closing, filing and blocking decision with a named person

Controls described in documents but not enforced

Run entitlement and known-outcome tests before every release, and keep the results

Measure the release on the alerts it changes: the share of alerts that close as false positives, the time it takes to assemble a case, how often a rationale is complete enough to stand on its own and whether every entitlement test passes. The ontology, its mappings, rules and tests stay in the bank's AWS account in open W3C formats, so the bank's own stewards can extend it.

Our context ontology services start from one question your agents or analysts keep getting wrong. Bring an alert your team closed and shouldn't have, the accounts behind it and the rationale, and within a week you get our findings, a proposed first-release scope and the date we would commit to.

FAQs

What is AI transaction monitoring?

AI transaction monitoring uses machine learning, and increasingly AI agents, to review payments and account activity for signs of money laundering, fraud or sanctions evasion. It works alongside or in place of fixed rules, and in AML it supports the bank's duty to detect suspicious activity and file reports on time.

How is AI used in AML transaction monitoring?
Mostly in three places: scoring activity so investigators see the riskiest alerts first, finding patterns that span many accounts, and assembling the evidence for a case. Agents can now gather that evidence and draft a rationale, while the decision to close an alert or file a SAR stays with a named person.
Does AI reduce false positives in transaction monitoring?
It can, when the false positives come from missing context such as a business whose cash volumes are normal for its account type. Measure it on your own alerts: run the new approach against cases your team has already closed and compare how many it would have raised and how many it would have missed.
What is a red flag in transaction monitoring?

A red flag is activity that doesn't fit what the bank knows about a customer, such as cash deposits kept just under the $10,000 reporting threshold or funds moving through an account faster than its stated business explains. FinCEN publishes red flags for specific typologies in its advisories, and banks turn them into monitoring scenarios.

What is a transaction ontology?
A transaction ontology is a governed, machine-readable model of each payment and everything that gives it meaning: the accounts, parties, beneficial owners, merchants, counterparties, products and rules involved. Monitoring systems and AI agents read it so they can group related activity and explain each alert.
What is FIBO, and do we need it?

FIBO, the Financial Industry Business Ontology, is an open standard written in OWL for financial concepts such as legal entities, ownership and control, accounts and financial products. It's maintained by the EDM Council with releases every quarter. A bank doesn't need all of it. We'd import the parts that match the first questions and add the bank's own scenarios and products.

What is a financial knowledge graph?

A financial knowledge graph is the ontology filled in with a bank's actual records, so customers, accounts, owners, merchants and payments are connected nodes a system can traverse. It's what lets a monitoring system or an agent follow one alert to every related party in a single query.

Does a transaction ontology replace our transaction monitoring system?
No. The monitoring system keeps scoring transactions and running scenarios. The ontology supplies the context those scenarios lack and maps data where it already lives, in core banking, card, KYC and case management, without moving it.
How do you keep AI from closing alerts or filing SARs on its own?
Give agents bounded authority and enforce it outside the model. An agent can gather evidence and draft a rationale, but closing an alert, filing a SAR or blocking a payment waits for a named person, and access to SAR-related information is denied by policy for every role that shouldn't see it.

 

Ammar Nizami, Senior Forward-Deployed Engineer, Data Engineering practice

Written by

Ammar Nizami

Senior Forward-Deployed Engineer, Data Engineering practice

Ammar leads a team of Forward-Deployed Engineers inside Mactores’ Data Engineering practice. Fifteen years in data engineering. Fifty-plus production Apache Iceberg engagements shipped. He owns the architecture calls that a customer’s data team cannot afford to get wrong — table format choice, partition strategy, migration sequencing, cutover under load — and hands the running platform back to the customer’s operations team on customer-signed acceptance. The complex Iceberg problems Mactores takes on are the ones his team solves.

Let's deliver

Bring us the process. We will bring the authority model.

The agent-native AWS modernization firm. Data platforms moved. Legacy retired. AI agents in production. AWS Premier Tier Services Partner since 2026, on AWS since 2008.

  • 01 AWS Premier Tier Services Partner, on AWS since 2008.
  • 02 Forward-deployed engineers own architecture, cutover and the date.
  • 03 Acceptance criteria per phase, with the signer named in the SOW.
  • 04 The golden set and the trace data belong to you.