3 types of fraud graph analytics can help defeat
1 like301 views
The document discusses how graph analytics can combat three types of fraud: insurance, credit card, and VAT fraud by leveraging connections between data points. It highlights the limitations of relational databases compared to graph databases, which can analyze complex relationships. Graph visualizations facilitate fraud detection by allowing investigators to see connections among individuals and transactions across various sources.
3 types of fraud graph analytics can help defeat
- 1. 3 types of fraud graph analytics can help defeat
- 2. 1. Insurance fraud 2. Credit card fraud 3. VAT fraud
- 3. Detecting fraud is about connecting the dots
- 4. But today’s applications fall short on more complex analysis that would imply several levels of relationships or data types RELATIONAL DATABASE ❌
- 5. In graph databases, connections are stored as 1st-class citizens, making it an interesting model for investigations. GRAPH DATABASE ✔
- 7. In insurance fraud, people team up to put together a fake road traffic accident claim reporting light personal injuries. Insurance companyInjury claim Injury claim Injury claim Staged accident Staged accident Staged accident Fraudster ring
- 8. The graph approach brings data from various sources under a common model. Investigators look at all the data together, instead of isolated data silos. Graph visualization of two customers (blue nodes) file three claims (green nodes). We identify a network of three customers connected through personal information such as phone (brown nodes), email (pink nodes) with the same lawyer (green node) involved every time. It is likely they are recycling stolen or fake identity to file fraudulent claims.
- 9. 2) Credit card fraud
- 10. Payment card fraud takes the form of criminals getting ahold of credit card information and proceeding to create unauthorized transactions. Compromised ATM Counterfeit card Counterfeit card Fraudster Counterfeit card Shop Shop
- 11. Graphs help identify the common point of compromise by highlighting the common links, no matter how large the dataset is. Graph visualization to identify a common point of compromise ATM: Clients (blue nodes), report fraudulent purchases (orange nodes). We can identify through connections the common ATM (purple) where they made a withdrawal before the card fraud.
- 12. 3) VAT fraud
- 13. Carousel fraud, or VAT fraud, is the theft of VAT collected on the sale of goods initially bought VAT-free in another jurisdiction. Company A Company B Disappear Company C VAT refund € € € Sell goods VAT free Sell goods, charges VAT
- 14. Graphs help identify the common point of compromise by highlighting the common links, no matter how large the dataset is. Graph visualization to identify chains of transactions in VAT fraud: Companies (blue nodes) and their parent organizations (flags nodes) sell goods VAT-free and collect back VAT through complex layers of sales between EU and non-EU countries.
- 15. Organizations use Linkurious Enterprise to fight fraud across activity sectors: insurance, banking, law enforcement or financial administrations.