How Entity Resolution Between Banks Can Crack Down on Mule Accounts

The world is facing a massive financial crime challenge — with billions lost globally to cyber fraud, banking fraud, and money laundering. Mule account networks are a critical enabler in these schemes, helping criminals move vast sums across borders while evading detection.

Fraudsters are getting smarter, and one of their most effective tactics today is the use of mule accounts — bank accounts that receive, move, or withdraw illicit funds on behalf of criminals. These accounts often look normal in isolation but are part of larger networks spread across multiple banks, making them incredibly hard to catch.

What if banks could connect the dots across institutions and see the bigger picture?

That’s where entity resolution (ER) between banks comes in.

The Mule Account Problem

Mule accounts are used in everything from phishing scams and loan fraud to international money laundering. They can be:

• Opened with fake or synthetic identities,

• Operated by people coerced or paid to “lend” their accounts,

• Or even recycled by fraudsters across different banks after being closed elsewhere.

  
  

Because mules are spread out and change constantly, no single bank has enough visibility to spot a pattern. One bank might flag a suspicious transaction, but if the same user is active at three other banks, those connections are often missed entirely.

The Power of Entity Resolution

Entity resolution is the process of identifying and linking records that refer to the same real-world person or device, even if their information looks different. For example:

• "A. Sharma" at Bank A might be the same person as "Ankit S." at Bank B, using a slightly different email and address.

• A device used to open an account at Bank X might also show up at Bank Y, under a different identity.

• A phone number flagged at one bank might be used again across several fintech apps.

By linking these records across institutions, ER gives us shared intelligence — helping banks uncover suspicious behaviors that are invisible in isolation.

How ER Helps Detect Mules

Here’s how cross-bank entity resolution directly helps in mule account detection:

1. Linking Identities Across Banks

Fraudsters tweak identities to avoid detection — slight name changes, new emails, altered KYC details. ER connects these fragments back to the same underlying entity.

2. Spotting Reused Devices and IPs

Even if the user information changes, their device fingerprint, IP address, or location pattern often stays the same. That’s a red flag.

3. Uncovering Network Behavior

Mules rarely work alone. ER helps build graphs of accounts, devices, and behaviors, revealing hidden relationships and mule rings that move money through interconnected accounts.

4. Catching Recycled Mules

Once flagged at one institution, fraudsters often try again elsewhere. ER helps prevent them from slipping through by sharing risk signals without sharing customer data.

Visual Example: How Entity Resolution Uncovers Mule Networks

The illustration above shows how inter-bank entity resolution transforms fragmented data into actionable fraud intelligence.

Before entity resolution, Bank A sees a large transfer from Account X to Y, and Bank B observes Account W sending funds to Z, flagged for involvement in a high-risk jurisdiction. On their own, neither bank sees the full picture.

But after entity resolution, it’s revealed that Accounts Y and W actually belong to the same entity — Organisation 2. This insight helps investigators understand the flow:

Organisation 1 ➝ Organisation 2 ➝ Organisation 3 (in a high-risk location)

The investigator can now track that Organisation 1 has been transferring a large sum of money to an organisation located in a high risk jurisdiction (Organisation 3).

Doing It Right: Privacy-Preserving ER

Banks can’t (and shouldn’t) share raw customer data. So how do you collaborate without violating privacy laws?

That’s where Privacy-Enhancing Technologies (PETs) come in:

Technology	What It Enables
Private Set Intersection (PSI)	Compare values like phone numbers or hashed emails across banks without revealing other data.
Homomorphic Encryption	Match or score records while everything stays encrypted.
Secure Multiparty Computation (SMPC)	Joint analysis over private data with no data leakage.

With these methods, banks can resolve common entities and detect shared risks, while staying fully compliant with regulations like GDPR or India’s DPDP Act.

The Outcome

With entity resolution, banks gain:

• Early warnings about repeat offenders,

• A way to identify networked fraud, not just isolated incidents,

• And a shared understanding of high-risk entities operating in the system.

It's like building an inter-bank radar—each bank contributes a signal, and together they form a complete view of fraudulent behavior. But this collaboration needs a secure and trusted environment — and that’s where Fraud Intelligence Clean Room plays a key role.

Reach out to us to learn more and explore how Pryvx can revolutionize your data collaboration efforts.