GraphGists

This interactive Neo4j graph tutorial covers bank fraud detection scenarios.

Introduction to Problem

Banks and Insurance companies lose billions of dollars every year to fraud. Traditional methods of fraud detection play an important role in minimizing these losses. However, increasingly sophisticated fraudsters have developed a variety of ways to elude discovery, both by working together and by leveraging various other means of constructing false identities.


Explanation of Scenario

While no fraud prevention measures can ever be perfect, significant opportunity for improvement lies in looking beyond the individual data points, to the connections that link them. Oftentimes these connections go unnoticed until it is too late-- something that is unfortunate, as these connections oftentimes hold the best clues.

Typical Scenario

While the exact details behind each first-party fraud collusion vary from operation to operation, the pattern below illustrates how fraud rings commonly operate:

  • A group of two or more people organize into a fraud ring

  • The ring shares a subset of legitimate contact information, i.e., phone numbers and addresses, combining them to create a number of fictional identities

  • Ring members open accounts using these fictional identities

  • New accounts are added to the original ones: unsecured credit lines, credit cards, overdraft protection, personal loans, etc.

  • The accounts are used as normally, with regular purchases and timely payments

  • Banks increase the revolving credit lines over time, due to the observed responsible credit behavior

  • One day the ring "busts out", coordinating their activity, maxing out all of their credit lines, and disappearing

  • Sometimes fraudsters will go a step further and bring all of their balances to zero using fake checks immediately before the prior step, doubling the damage

  • Collections processes ensue, but agents are never able to reach the fraudster

  • The uncollectible debt is written off


Explanation of Solution

Graph databases offer new methods of uncovering fraud rings and other sophisticated scams with a high degree of accuracy, and are capable of stopping advanced fraud scenarios in real time.

How Graph Databases Can Help

Augmenting one’s existing fraud detection infrastructure to support ring detection can be done by running appropriate entity link analysis queries using a graph database, and running checks during key stages in the customer & account lifecycle, such as:

  • At the time the account is created

  • During an investigation

  • As soon as a credit balance threshold is hit

  • When a check is bounced

Real time graph traversals tied to the right kinds of events can help banks identify probable fraud rings, during or even before the Bust-Out occurs.


Bank Fraud Graph Data Model

Graph databases have emerged as an ideal tool for overcoming these hurdles. Languages like Cypher provide a simple semantic for detecting rings in the graph, navigating connections in memory, in real time.

The graph data model below represents how the data actually looks to the graph database, and illustrates how one can find rings by simply walking the graph:

Bank Fraud
Figure 1. Bank Fraud

Sample Data Set


Performing entity link analysis on the above data model is demonstrated below. We use brackets in the below table is to isolate individual elements of a collection.

Find account holders who share more than one piece of legitimate contact information

MATCH 		(accountHolder:AccountHolder)-[]->(contactInformation)
WITH 		contactInformation,
			count(accountHolder) AS RingSize
MATCH 		(contactInformation)<-[]-(accountHolder)
WITH 		collect(accountHolder.UniqueId) AS AccountHolders,
			contactInformation, RingSize
WHERE 		RingSize > 1
RETURN 		AccountHolders AS FraudRing,
			labels(contactInformation) AS ContactType,
			RingSize
ORDER BY 	RingSize DESC

Determine the financial risk of a possible fraud ring

MATCH 		(accountHolder:AccountHolder)-[]->(contactInformation)
WITH 		contactInformation,
			count(accountHolder) AS RingSize
MATCH 		(contactInformation)<-[]-(accountHolder),
			(accountHolder)-[r:HAS_CREDITCARD|HAS_UNSECUREDLOAN]->(unsecuredAccount)
WITH 		collect(DISTINCT accountHolder.UniqueId) AS AccountHolders,
			contactInformation, RingSize,
			SUM(CASE type(r)
				WHEN 'HAS_CREDITCARD' THEN unsecuredAccount.Limit
				WHEN 'HAS_UNSECUREDLOAN' THEN unsecuredAccount.Balance
				ELSE 0
			END) as FinancialRisk
WHERE 		RingSize > 1
RETURN 		AccountHolders AS FraudRing,
			labels(contactInformation) AS ContactType,
			RingSize,
			round(FinancialRisk) as FinancialRisk
ORDER BY 	FinancialRisk DESC