how to apply graph analytics for bank loan fraud detection?
DESCRIPTION
A walk through a common fraud case : how to use Neo4j and graph visualization to identify criminals and fight loan fraud.TRANSCRIPT
How to apply graph analytics for bank loan fraud detection?
SAS founded in 2013 in Paris | http://linkurio.us | @linkurious
WHAT IS A GRAPH?
Father Of
Father Of
Siblings
This is a graph
WHAT IS A GRAPH : NODES AND RELATIONSHIPS
Father Of
Father Of
Siblings
A graph is a set of nodes linked by relationships
This is a node
This is a relationship
People, objects, movies, restaurants, music
Antennas, servers, phones, people
Supplier, roads, warehouses, products
Graphs can be used to model many domains
DIFFERENT DOMAINS WHERE GRAPHS ARE IMPORTANT
Supply chains Social networks Communications
But why can graphs can help identify fraud?
GRAPH AND FRAUD DETECTION
AITE Group estimates that first party fraud will cost $28.6 billion in credit card losses a year by 2016.
THE COST OF FRAUD
A look at a common fraud scenario banks face
A COMMON FRAUD SCENARIO
Create a fake identity
Go to the bank, ask for a loan
Disappear with the money
A criminal uses the fake identity to register a bank
account. He acts like a normal customer and tries to
secure a loan
Once the criminal feels he cannot get access to more
money he carefully prepares his exit : in a short amount of
time he empties all of his accounts and disappears
A criminal or a group of criminal mix pieces of
information (addresses, phone numbers, social
security number) to create a “synthetic-identity”
THE PAINS OF WORKING ON CONNECTED DATA WITH RELATIONAL TECHNOLOGIES
Relational databases are not good at handling... relationships
Depth RDBMS execution time (s) Neo4j execution time (s) Records returned
2 0.016 0.01 ~2500
3 30.267 0.168 ~110 000
4 1543.505 1.359 ~600 000
5 Unfinished 2.132 ~800 000
Finding extended friends in a 1M people social network (from the book Graph Databases)
Loan$25k
Home address58, Eisenhower Square
A GRAPH DATA MODEL FOR FRAUD DETECTION
Customer nameJ. Smith
Phone number+33 5 68 98 25 74
The first step to detect fake identity is to use a graph to model customer information
Credit card1 234$
IDJ. Smith
A graph showing a legitimate customer and the information she is linked to
In a fraud ring people share the same information
A LOOK AT A FRAUD RING THROUGH GRAPH VISUALIZATION
58, Eisenhower Square
14, Roses Street
+33 6 75 89 22 14
$7k
P. Martin
$12,5k +331 42 58 66 00
J. Smith
SSN 17873897893
8, Sugar Hill Street
$20k
E. Selmati
SSN 1787576553
$45k
P. Smith
SSN 1787579953SSN 1267576553
8, Coronation Street
HOW TO APPLY IT IN THE REAL WORLD
Graph databases makes it possible to identify the fraud patterns in real-time
Lifecycle events trigger security checks
A new customer opens an account
An existing customer asks for a loan
A customer skips a loan payment
A Neo4j Cypher query runs to detect patterns
The bank can make an informed decision
The fraud teams acts faster and more fraud cases can be
avoided.
WHAT IS THE IMPACT OF LINKURIOUS
If something suspicious comes up, the analysts can use Linkurious to quickly assess the
situation
Linkurious allows the fraud teams to go deep in the data and build cases against fraud
rings.
Treat false positives
Investigate serious cases
Save money
Linkurious allows you to control the alerts and make sure your customers are not
treated like criminals.
TECHNOLOGY
Cloud ready and open-source based
OTHER USE CASES
Graphs are everywhere, learn to leverage them
Detailed use case on our blog :
● Part 1 : http://linkurio.us/how-to-detect-bank-loan-fraud-with-graphs-part-1/● Part 2 : http://linkurio.us/how-to-detect-bank-loan-fraud-with-graphs-part-2/● Neo4j data set : https://www.dropbox.com/s/wk8k5r23syp6kbx/fraud%20detection.zip
GraphGist by Kenny Bastani : http://gist.neo4j.org/?github-neo4j-contrib%2Fgists%2F%2Fother%2FBankFraudDetection.adoc
Video demonstration : https://vimeo.com/76891393 (around the 12 minutes mark)
ADDITIONAL RESOURCES