PSD2 and fraud monitoring – redefining payment security and compliance
The Payment Services Directive 2 (PSD2) fundamentally changed how banks and payment providers detect and prevent fraud. Introduced to enhance consumer protection and encourage innovation, PSD2 required every financial institution operating in the EU to reengineer its transaction monitoring systems.
The PSD2 framework
- Strong Customer Authentication (SCA): mandatory multi-factor authentication for digital payments.
- Transaction Risk Analysis (TRA): dynamic assessment of transaction risk to enable SCA exemptions.
- Real-time monitoring: continuous evaluation of payment behavior to identify anomalies.
- Incident reporting: regulated procedures for communicating security breaches to authorities.
How PSD2 changed fraud monitoring
Key shifts include:
- From static to dynamic: algorithms adjust thresholds and risk scores continuously.
- From siloed to integrated: payment data, authentication events, and device data now feed a unified fraud engine.
- From detection to prediction: AI and analytics forecast risk instead of reacting after losses.
- From compliance to resilience: monitoring systems now serve both regulatory and security objectives.

Fraud types targeted under PSD2
According to the European Central Bank’s 2024 Payment Fraud Report, PSD2 has significantly reduced card-not-present fraud, but new threats continue to evolve. Common risks include:- Account takeover through phishing or malware.
- Synthetic identities combining real and fake data.
- Transaction manipulation via compromised APIs.
- Fraudulent third-party payment initiation.
How a new approach to financial crime could stop
fraud in its tracks
The proof-of-concept 2019 changed the frame: instead of judging each payment on its own, it followed how money travels across accounts and institutions. That shift revealed patterns single-transaction systems miss.

The scale is staggering. Financial institutions together spend an estimated $200 billion a year on compliance and AML, and yet fraud losses remain stubbornly high-costing banks and customers tens of billions annually.
What's inside?
-
Seeing the whole network
- A shared defense with measurable impact
and more...
The role of Transaction Risk Analysis (TRA)
To qualify for exemptions, firms must demonstrate:
- Proven fraud rates below defined thresholds.
- Continuous, AI-supported monitoring.
- Clear escalation and reporting mechanisms.
“PSD2 didn’t just tighten authentication; it changed how institutions think about trust. Fraud detection has moved from rule-based control to continuous intelligence.”
- William Morris, Lead Enterprise Account Executive - UK
Cross-regulatory connections
- AMLD6 and AMLD5, which define the broader anti-money laundering architecture.
- EBA Guidelines on Financial Crime Risk, which extend monitoring obligations.
- DORA, which ensures resilience in fraud detection systems.
- FATF Recommendations, which provide the international benchmark for AML and CTF compliance.
Read Suspicious Activity Monitoring for insight into reporting integration.
See Financial Crime Detection to understand how AI supports PSD2 monitoring.
Explore Regulatory Technology (RegTech) to see how innovation supports PSD2 compliance.
Challenges in PSD2 fraud monitoring
- Integrating multiple authentication and monitoring systems.
- Managing third-party access through open banking APIs.
- Complying with data protection requirements under GDPR.
- Maintaining consistent risk thresholds across jurisdictions.
Partisia’s perspective
Using Multi-Party Computation (MPC), banks and payment providers can:
- Correlate transaction data across institutions without exposing customer details.
- Train fraud detection models collaboratively and securely.
- Meet both PSD2’s transparency obligations and GDPR’s privacy restrictions.
2025.11.03