Leveraging graph technology to fight financial fraud
1 like•144 views
1) Traditional fraud detection methods like analyzing endpoints, navigation behavior, and accounts discretely are unable to detect modern complex fraud schemes. 2) Connected analysis using graph databases can model relationships between entities to detect organized fraud rings and synthetic identities in real-time. 3) A demo showed how Neo4j augments existing fraud detection systems by performing sub-second connected analysis of user transactions to quickly identify fraudulent patterns and adapt to new fraud methods.
Leveraging graph technology to fight financial fraud
- 1. LEVERAGING GRAPH-TECHNOLOGY TO FIGHT FINANCIAL FRAUD
- 2. AGENDA • Meet today’s fraudsters • Traditional fraud detection methods • Using connected analysis for real-time fraud detection • Demo • Summary
- 4. The Impact of Fraud The payment card fraud alone, constitutes for over 16 billion dollar in losses for the bank-sector in the US. $16Bpayment card fraud in 2014* Banking $32Byearly e-commerce fraud** Fraud in E-commerce is estimated to cost over 32 billion dollars annually is the US.. E-commerce The impact of fraud on the insurance industry is estimated to be $80 billion annually in the US. Insurance $80Bestimated yearly impact*** *) Business Wire: http://www.businesswire.com/news/home/20150804007054/en/Global-Card-Fraud-Losses-Reach-16.31-Billion#.VcJZlvlVhBc **) E-commerce expert Andreas Thim, Klarna, 2015 ***) Coalition against insurance fraud: http://www.insurancefraud.org/article.htm?RecID=3274#.UnWuZ5E7ROA
- 6. Who Are Today’s Fraudsters?
- 7. Organized in groups Synthetic Identities Stolen Identities Who Are Today’s Fraudsters? Hijacked Devices
- 8. “Don’t consider traditional technology adequate to keep up with criminal trends” Market Guide for Online Fraud Detection, April 27, 2015
- 9. Endpoint-Centric Analysis of users and their end-points 1. Navigation Centric Analysis of navigation behavior and suspect patterns 2. Account-Centric Analysis of anomaly behavior by channel 3. PC:s Mobile Phones IP-addresses User ID:s Comparing Transaction Identity Vetting Traditional Fraud Detection Methods
- 10. Unable to detect • Fraud rings • Fake IP-adresses • Hijacked devices • Synthetic Identities • Stolen Identities • And more… Weaknesses DISCRETE ANALYSIS Endpoint-Centric Analysis of users and their end-points 1. Navigation Centric Analysis of navigation behavior and suspect patterns 2. Account-Centric Analysis of anomaly behavior by channel 3. Traditional Fraud Detection Methods
- 11. INVESTIGATE Revolving Debt Number of Accounts INVESTIGATE Normal behavior Fraud Detection With Discrete Analysis
- 12. Revolving Debt Number of Accounts Normal behavior Fraud Detection With Connected Analysis Fraudulent pattern
- 13. CONNECTED ANALYSIS Augmented Fraud Detection Endpoint-Centric Analysis of users and their end-points Navigation Centric Analysis of navigation behavior and suspect patterns Account-Centric Analysis of anomaly behavior by channel DISCRETE ANALYSIS 1. 2. 3. Cross Channel Analysis of anomaly behavior correlated across channels 4. Entity Linking Analysis of relationships to detect organized crime and collusion 5.
- 14. ACCOUNT HOLDER 2 Modeling a fraud ring as a graph ACCOUNT HOLDER 1 ACCOUNT HOLDER 3
- 15. ACCOUNT HOLDER 2 Modeling a fraud ring as a graph ACCOUNT HOLDER 1 ACCOUNT HOLDER 3 CREDIT CARD BANK ACCOUNT BANK ACCOUNT BANK ACCOUNT PHONE NUMBER UNSECURED LOAN SSN 2 UNSECURED LOAN
- 16. ACCOUNT HOLDER 2 Modeling a fraud ring as a graph ACCOUNT HOLDER 1 ACCOUNT HOLDER 3 CREDIT CARD BANK ACCOUNT BANK ACCOUNT BANK ACCOUNT ADDRESS PHONE NUMBER PHONE NUMBER SSN 2 UNSECURED LOAN SSN 2 UNSECURED LOAN
- 17. ACCOUNT HOLDER 2 Modeling a fraud ring as a graph ACCOUNT HOLDER 1 ACCOUNT HOLDER 3 CREDIT CARD BANK ACCOUNT BANK ACCOUNT BANK ACCOUNT ADDRESS PHONE NUMBER PHONE NUMBER SSN 2 UNSECURED LOAN SSN 2 UNSECURED LOAN SYNTETIC PERSON 2 SYNTHETIC PERSON 1
- 18. FRAUD DEMO
- 19. USING NEO4j FOR REAL-TIME CONNECTED ANALYSIS
- 20. Account-Centric Analysis of anomaly behavior correlated across channels 4. Entity Linking Analysis of relationships to detect organized crime and collusion 5. CONNECTED ANALYSIS Endpoint-Centric Analysis of users and their end-points Navigation Centric Analysis of navigation behavior and suspect patterns Account-Centric Analysis of anomaly behavior by channel DISCRETE ANALYSIS 1. 2. 3. Augment Fraud Detection with Neo4j Traditional Vendors
- 21. ACCEPT / DECLINE MANUAL User/Transaction CONNECTED ANALYSIS User/Transaction ACCEPT / DECLINE(DISCRETE ANALYSIS) + User/Transaction (sub-second performance to any data size and connection) ACCEPT / DECLINE REAL TIME TRADITIONAL VENDORS (DISCRETE ANALYSIS) (DISCRETE ANALYSIS) ACCEPT / DECLINE How Neo4j fits in
- 22. Detect & prevent fraud in real-time Faster credit risk analysis and transactions Reduce chargebacks Quickly adapt to new methods of fraud Why Neo4j? Who’s using it? Financial institutions use Neo4j to: FINANCE Government Online Retail
- 23. • Today’s fraudsters are organized and highly sophisticated • Legacy technology does not detect fraud sufficiently and in real-time • Graph-databases enable you to discover fraudulent patterns in real- time • Augment your current fraud detection infrastructure with connected analysis KEY TAKE AWAYS
- 24. THANK YOU!