Transaction monitoring
in real time

DetectX® checks each payment as it is filtered against a threshold learned for that customer, so the same amount can be normal for one client and an alert for another. Thresholds come from the customer’s own history and from customers who behave like them, and they adjust as the data changes.

Request a demoTalk to us
  1. 1Ingest
  2. 2Evaluate
  3. 3Alert
  4. 4Investigate
  5. 5Platform tour
DetectX - One Platform. Total Compliance (FINAL CAPTIONS)

One Platform. Total Compliance.

The DetectX® Approach

Every payment, against the customer’s own limit.

Real-time transaction monitoring is the checking of each payment for unusual or suspicious activity while it is being processed, rather than in an end-of-day batch. In DetectX®, Behavioural Analysis learns a threshold for every customer from their own history and from customers like them, and Transaction Filtering applies it in the rules that check each payment.

A limit that fits the customer, on the payment itself. Behavioural Analysis gives each customer a threshold of their own. Integrated with Transaction Filtering, it is applied in the rules that check each payment.

Your core systemEach PaymentSent for filtering before it is processed.
Behavioural AnalysisEach Customer’s ThresholdLearned from their history and their cluster.
Transaction FilteringYour Business RulesThe payment is compared with the customer’s own threshold and behavioural risk.
  • Single transaction
  • Cumulative over one or three days
  • Transaction behavioural risk
Above the thresholdAn Alert Is RaisedOn the payment, as it is filtered.
Your analystWorks the AlertIn AlertViewer, with every other alert.

Real-time alerting is an optional integration with Transaction Filtering, with additional implementation effort

Key Benefits & Impact

The same amount means different things for different customers.

A fixed limit treats every customer the same. DetectX® gives each customer a limit learned from their own behaviour, checks each payment against it as it is filtered, and raises an alert your analysts can act on.

Normal for One, Unusual for Another

The same payment, judged against who makes it.

Each customer has a threshold learned from their own history and from customers like them. A payment that is routine for one client raises an alert for another, and one fixed limit no longer decides for both.

How each threshold is learned
Alerts on the Payment

An alert the same day, not the next morning.

With Transaction Filtering, each payment is checked against the customer’s threshold as it is filtered. The alert reaches your analysts while the payment is current, not in the next batch.

The rules that check each payment
Small Payments Add Up

Splitting a payment does not hide it.

Rules can compare a single payment or the total over one or three days with the customer’s threshold. Payments that each stay below the limit still raise an alert when together they pass it.

Spotting patterns across payments
Limits That Keep Up

A limit that moves when the customer does.

Thresholds are set by the system rather than fixed in advance, and adjust as the customer base or the wider economy changes. Nobody has to retune a limit by hand every time a client grows.

How customers are clustered
Rules Your Team Owns

Your policy, with each customer’s limit built in.

The customer threshold and behavioural risk become variables in your business rules. Your compliance team decides which conditions raise an alert, and changes them without waiting for a release.

Writing rules with these values
Built on What You Already Know

Real time added to monitoring you already run.

The clustering model starts in Client Risk Scoring, daily alerts come from Transaction Monitoring, and real time is added through Transaction Filtering. Every alert lands in the AlertViewer your team already uses.

Where the clustering model starts

Why DetectX®

Most monitoring uses one limit for everyone. DetectX® uses theirs.

Request a demoTalk to our team
  • A limit per customerThe same CHF 10,000 for a trading company and a retail clientA threshold learned from each customer’s own history and from customers like themBehavioural Analysis
  • Routine stays quietLarge clients alert on payments they make every monthA payment within the customer’s own threshold raises no alertHow each threshold is learned
  • Split payments seenThree payments under the limit pass unseenSingle payments or totals over one or three days checked against the thresholdKey benefits
  • Limits that keep upOne number, revisited at the next reviewThresholds set by the system adjust as the data changesHow customers are clustered
  • Alert on the paymentFound in the next batch, if at allChecked as each payment is filtered, so the alert reaches your analysts the same dayTransaction Filtering
  • Inside the rules you writeA limit hard-coded outside your rulesCustomer threshold and behavioural risk are variables in your business rulesBusiness Rules Design & Engine

In production

Values per Customer

Your rules, with each customer’s own limit inside them.

4 Values in Your Rules

Four values become variables in your business rules: the behavioural cluster, behavioural risk, the customer threshold and the behavioural risk of the payment.

Business Rule Engine

Your Next Step

Three ways in, depending on where you are.

Each one is a conversation with the people who build DetectX®, with no obligation.

Start Here

Request a Demo

Watch Real-time Transaction Monitoring work through real alerts with a product specialist.

  • Alerts explained, field by field
  • Thresholds tuned in front of you
  • Your questions answered on the call
30 min · Video callRequest

Talk to Our Team

Bring your data, volumes and core banking system. We map where DetectX® fits.

  • How DetectX® connects to your systems
  • Which data you would use
  • A realistic plan for going live
45 min · Video callBook a call

Ask for a Reference

Speak with a compliance team already running DetectX®.

  • A peer with a set-up close to yours
  • Their experience, in their words
  • Arranged with their agreement
By arrangement · CallAsk us

How Real-time Transaction Monitoring Works

Try it yourself: four steps, from a customer’s own limit to a decision on the payment.

The same CHF 18,500 can be normal for one customer and unusual for another. Behavioural Analysis gives every customer a threshold of their own, and through Transaction Filtering it is applied to each payment as it is filtered. Every step is yours to drive.

Illustrative exampleInvented Names & Data

Explore the DetectX® Platform

Start with Real-time Transaction Monitoring. Add what you need next.

Every DetectX® solution runs on the same underlying platform and shares its capabilities, AlertViewer and audit trail. Pick a solution to see what it adds to Real-time Transaction Monitoring.

All solutions
Business IntelligenceWorkflowsRegulatory Reporting

Real-time Transaction Monitoring FAQs

What compliance teams ask before choosing DetectX®.

Something we have not covered?Talk to our team

Real-time transaction monitoring is the checking of each payment for unusual or suspicious activity while it is being processed, rather than in an end-of-day batch. In DetectX®, Behavioural Analysis learns a threshold for every customer, and Transaction Filtering applies it in the rules that check each payment. A payment outside the customer’s normal behaviour raises an alert.

SolutionTransaction Filtering

Transaction Monitoring runs at the end of the day over every transaction, measuring each one against the customer’s history to find patterns a single payment cannot show. Real-time Transaction Monitoring checks each payment as it is filtered, against the customer’s own threshold. The two run side by side, and their alerts arrive in the same AlertViewer.

SolutionTransaction Monitoring

The system sets it. Customers are grouped into clusters with similar behaviour, and each customer’s activity is compared with their own history and with their cluster. The threshold is learned from both comparisons and adjusts as the customer base or the wider economy changes.

SolutionBehavioural Analysis

Yes. Behavioural Analysis calculates four values for each customer: behavioural cluster, behavioural risk, customer threshold and the behavioural risk of the payment. They become variables in your business rules, so your compliance team can compare a single payment, or the total over one or three days, with the customer’s threshold.

PlatformBusiness Rule Engine

Alerts are generated monthly and daily as standard. Real-time alerting on each payment is an optional integration with Transaction Filtering. A payment with a behavioural risk above 0.8 to 0.9 normally raises an alert, and the exact cut-offs are set in your rules.

PlatformPattern Recognition

Client Risk Scoring builds the initial clustering model, Transaction Monitoring generates the daily alerts, and Transaction Filtering adds real-time alerting. Before go-live, the model is built on your own data. At least two years of history is recommended to shorten the start.

SolutionClient Risk Scoring

Go Deeper

All resources
InsightHow Real Time Transaction Monitoring Prevents Financial Crime

Why checking payments as they are processed catches what an end-of-day run finds too late. It also covers how behavioural analytics helps separate unusual activity from the routine.

Read the articleCase studyFinnova Analytical Framework

How a Swiss banking software provider embedded DetectX® into the Finnova Analytical Framework. Behavioural Analysis and Real-time Transaction Monitoring are available there as options for the banks that run it.

Read the case studyInsightThe Impact of False Positives in AML and How to Reduce Them

What false positives cost a compliance team, where they come from, and why judging each payment against the customer’s own behaviour produces fewer of them than a single fixed limit.

Read the article

Real-time Transaction Monitoring · DetectX®

See Real-time Transaction Monitoring in a demo

Book a working session on your own transaction flow. Bring your questions about latency, rule design and what your deployment can act on in real time.

Request a demoTalk to us
Real-time
Vast volumes analysed as they arrive, with advanced algorithms and fuzzy matching.
98% fewer false alerts
Observed at a Swiss retail bank using the DetectX® platform.
One platform
Monitoring, screening and behavioural analysis on the same core and the same queue.