Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.

How to Build a Fraud Detection Solution with Neo4j

948 vues

Publié le

Joe Depeau, Neo4j

Publié dans : Technologie
  • Soyez le premier à commenter

How to Build a Fraud Detection Solution with Neo4j

  1. 1. How to Build a Fraud Detection Solution with Neo4j Joe Depeau Sr. Presales Consultant, UK 18th July, 2018 @joedepeau http://linkedin.com/in/joedepeau
  2. 2. • Who are Today’s Fraudsters? • Fraud Detection from a Data Modelling Perspective • How to Fight Fraud Rings with Graphs • A Closer Look at Credit Card Fraud • How Neo4j Fits in a Typical Architecture • Demo • Summary • Q & A 2 Agenda
  3. 3. Who are Today’s Fraudsters? 3
  4. 4. 4 Who Are Today’s Fraudsters?
  5. 5. 5 Organized in groups Synthetic Identities Stolen Identities Hijacked Devices Who Are Today’s Fraudsters?
  6. 6. 6 Types of Fraud • Credit Card Fraud • Rogue Merchants • Fraud Rings • Insurance Fraud • eCommerce Fraud • Fraud we don’t know about yet…
  7. 7. 7 Digitized and Analog World of Fraud Constantly Evolving Few and Many Players “One Step Ahead” Simple and Complex
  8. 8. Fraud Detection (from a data modelling perspective) 8
  9. 9. 9 Raw Data
  10. 10. 10 Anomalies
  11. 11. 11 Patterns
  12. 12. 12 1) Detect 2) Respond Fraud Prevention is About Reacting to Patterns (And doing it fast!)
  13. 13. 13 Relational Database Choosing Underlying Technology
  14. 14. 14 Data Modelled as a Graph! Graph Database
  15. 15. 15 ACCOUNT HOLDER 2 Modeling a fraud ring as a graph ACCOUNT HOLDER 1 ACCOUNT HOLDER 3
  16. 16. 16 ACCOUNT HOLDER 2 ACCOUNT HOLDER 1 ACCOUNT HOLDER 3 CREDIT CARD BANK ACCOUNT BANK ACCOUNT BANK ACCOUNT PHONE NUMBER UNSECURED LOAN SSN 2 UNSECURED LOAN Modeling a fraud ring as a graph
  17. 17. 17 ACCOUNT HOLDER 2 ACCOUNT HOLDER 3 CREDIT CARD BANK ACCOUNT BANK ACCOUNT BANK ACCOUNT ADDRESS PHONE NUMBER PHONE NUMBER SSN 2 UNSECURED LOAN SSN 2 UNSECURED LOAN Modeling a fraud ring as a graph ACCOUNT HOLDER 1
  18. 18. How to Fight Fraud Rings with Graphs 18
  19. 19. 19 “Don’t consider traditional technology adequate to keep up with criminal trends” Market Guide for Online Fraud Detection, April 27, 2015
  20. 20. 20 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 Layered Model for Fraud Prevention (https://www.gartner.com/newsroom/id/1695014)
  21. 21. 21 Unable to detect • Fraud rings • Fake IP-addresses • 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 Layered Model for Fraud Prevention (https://www.gartner.com/newsroom/id/1695014)
  22. 22. 22 INVESTIGATE Revolving Debt Number of Accounts INVESTIGATE Normal behavior Fraud Detection with Discrete Analysis
  23. 23. 23 Revolving Debt Number of Accounts Normal behavior Fraudulent pattern Fraud Detection with Connected Analysis
  24. 24. 24 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 Cross Channel Analysis of anomaly behavior correlated across channels 4 Entity Linking Analysis of relationships to detect organized crime and collusion 5 Augmented Fraud Detection Layered Model for Fraud Prevention (https://www.gartner.com/newsroom/id/1695014)
  25. 25. 25
  26. 26. Blank Slide 26
  27. 27. A Closer Look at Credit Card Fraud 27
  28. 28. 28 Manual skimming of an ATM Sophisticated Data Breaches Retrieval of Credit Card Information Rogue Merchant
  29. 29. 29 USE ISSUES Terminal ATM- skimming Data Breach Card Holder Card Issuer Fraudster USE $5MAKES $10 MAKES $2 MAKES MAKES $4000 AT Testing Merchants ATMAKES Tx
  30. 30. 30 TxTx $2 TxTx Tx $2000 Tx Tx $25$10$4 TxTx Tx Tx TxTxTx Computer Store John Gas Station Sheila Robert $3 Karen TxTxTx Tx Tx TxTx $3000 Tx Jewelry StoreTx $3 TxTxTx Tx Tx TxTx TxTx TxTx TxTx Tx Tx TxTx $8 $12 Tx $1500 Furniture Store Tx Tx Tx
  31. 31. How Neo4j Fits in a Typical Architecture 31
  32. 32. 32 Money Transferring Purchases Bank Services Relational databases Develop Patterns Data Science team + Good for Discrete Analysis – No Holistic View of Data-Relationships – Slow query speed for connections
  33. 33. 33 Money Transferring Purchases Bank Services Relational databases Data Lake +Good for Map Reduce +Good for Analytical Workloads – No holistic view – Non-operational workloads – Weeks-to-months processes Develop Patterns Data Science team Merchant Data Credit Score Data Other 3rd Party Data
  34. 34. 34 Money Transferring Purchases Bank Services Neo4j powers 360° view of transactions in real-time Neo4j Cluster SENSE Transaction stream RESPOND Alerts & notification LOAD RELEVANT DATA Relational databases Data Lake Visualization UI Fine Tune Patterns Develop Patterns Data Science team Merchant Data Credit Score Data Other 3rd Party Data LOAD RELEVANT DATA
  35. 35. 35 Money Transferring Purchases Bank Services Neo4j powers 360° view of transactions in real-time Neo4j Cluster SENSE Transaction stream RESPOND Alerts & notification Relational databases Data Lake Visualization UI Fine Tune Patterns Develop Patterns Data Science team Merchant Data Credit Score Data Other 3rd Party Data Data-set used to explore new insights LOAD RELEVANT DATA LOAD RELEVANT DATA
  36. 36. Demo 36
  37. 37. Q & A 37
  38. 38. 38 Valuable Resources! neo4jsandbox.com https://neo4j.com/use-cases/fraud-detection/ neo4j.com/product Sandbox Fraud Detection Product

×