Fraud Detection with Neo4j
5 likes2,610 views
The document discusses using Neo4j and graph databases for fraud detection solutions. It describes how Neo4j allows for agile development, high productivity, and real-time response times when working with connected fraud data. The document outlines a fraud detection demo using Neo4j to load operational data, inject fraud cases, generate alerts, and export detected fraud data for investigation. It proposes using Neo4j as the foundation for a 360-degree fraud prevention solution integrated with other systems and data sources.
Fraud Detection with Neo4j
- 2. Retail Banking First-Party Fraud Opening many lines of credit with no inten5on of paying them back Causing High Impact • Tens of billions of dollars lost every year by U.S. Banks.(1) • 25% of total consumer credit charge-offs in the United States.(2) • 10% to 20% of unsecured bad debt at leading U.S. and European banks is misclassified, and is actually first-party fraud.(3) (1) Experian: hQp://www.experian.com/assets/decision-analy5cs/white-papers/first-partyfraud-wp.pdf (2) Experian: hQp://www.experian.com/assets/decision-analy5cs/white-papers/first-partyfraud-wp.pdf (3) Business Insider: hQp://www.businessinsider.com/how-to-use-social-networks-in-the-fight-against-first-party-fraud-2011-3
- 4. Fraud Demo – Part I (generic) • Fraud scenario covering Retail Fraud use cases • Data set contains opera5onal data • Constant data load –> injec5ng fraud cases -> generate alerts • Capability to export data of detected fraud for further inves5ga5on Neo4j App Server Fraud Detec5on Web App Fraud App Browser UX: TestDataGen Alert generated
- 5. Demo
- 6. Why using GraphDB / Neo4j for Fraud? • Agile Development • High produc5vity and rapid implementa5on • No “RDBMS-waterfall-high-investment-trap” • Taking advantage of the full value of connected data • Traversing the graph compared to self joins in RDBMS • Near real 5me response 5mes • Preven5ng fraud rather than detec5ng ader the fact • Schema free • Nodes can vary depending on 5me / usage / seman5c
- 7. • Usage scenario Fraud Analyst: • Poten5al fraud case detected • Enriched with data from various sources containing data on fraud suspect • Trigger human and/or automated reac5ons Fraud Demo – Part II Neo4j Web App Data Integra5on RDBMS (Oracle, MySQL, DB2, HANA …) Management Console (E.g BI Tools such as Tableau, Qlik, BO, MicroStrategy etc) Fraud Analyst Machine2Machine generated ac5ons Alert Incoming Events CRM System Opera5onal System External Data
- 9. Conclusions • Fraud as one use case to provide full value of connected data within the en5re organiza5on • Neo4j as the founda5on to do 360 degree fraud detec5on and preven5on • Neo4j to extend your exis5ng environment while protec5ng your investments • Neo4j provides best value integrated in the en5re environment • Neo4j as the founda5on for genera5ng real 5me alerts to trigger automated or manual interven5ons
- 10. Encore