Enterprises leverage graph databases to get a handle on complex fraud challenges: Neo4j
Enterprises leverage graph databases to get a handle on complex fraud challenges: Neo4j : Each and every industry in existence is, or will soon be, under attack by groups of fraudsters. What’s the secret for enterprises to stop these criminals before it’s too late? Neo Technology, creator of Neo4j, the world’s leading graph database, says using real-time graph queries is the most powerful way to detect a variety of highly-impactful fraud scenarios. From fraud rings and collusive groups, to operations by educated criminals working on their own, graph databases provide a unique ability to uncover a variety of important fraud patterns, in real-time.As traditional fraud identification methods rely on outliers and the tracking of abnormal behavior, today’s businesses struggle with identifying and preventing fraud in real-time, by leveraging via more subtle clues via entity-linked analysis. Graph databases have emerged as an ideal tool for overcoming this hurdle, given their ability to query intricate connected networks, which can be used to identify fraud rings in a straightforward fashion.
“Graph databases are a unique tool for fraud detection because they have the ability to connect a ring of perpetrators and their activities to detect fraud instances as they happen. Collusions previously hidden are now obvious when you look at them with a system designed to manage connected data,” said Emil Eifrem, founder and CEO of Neo Technology. “Simply put, Neo4j stops the bad guys at the front door. This is the most sophisticated way of identifying fraud and makes organizations much more agile.”
Types of Fraud
Three of the most damaging types of fraud today include first-party bank fraud, insurance fraud, and e-commerce fraud. While these three are entirely different types of scams, they hold one very important commonality: each involves deception that relies upon layers of indirection that can be uncovered through analysis of connected data.
1. First-Party Bank Fraud involves fraudsters who apply for credit cards, loans, overdrafts and unsecured banking credit lines, with no intention of paying them back. It is a serious problem for banking institutions, costing over tens of billions of dollars every year.1Catching fraud rings and stopping them before they inflict damage is a challenge because traditional methods of fraud detection are not geared to look for the right thing. Standard instruments—such as a deviation from normal purchasing patterns— use discrete data rather than analysis of indirect connections that can signal fraud. Discrete methods are useful for catching fraudsters acting alone, but they fall short in their ability to detect rings. Further, many such methods are prone to false positives, which create undesired side effects in customer satisfaction and lost revenue opportunity.
2. Insurance Fraud: The impact of fraud on the insurance industry is estimated to be $80 billion annually in the US, a number that has been growing in recent years.2 As with bank fraud detection, a layered approach has emerged as a best practice for detecting insurance fraud. While existing analysis techniques are sufficient for catching certain kinds of fraud scenarios, sophisticated criminals often elude these methods through collaboration. Criminal rings are very skilled at concealing collusion, and at inventing and staging complex “paper collisions” that do not arouse suspicion. The next frontier in Insurance Fraud detection is to use social network analysis to uncover these rings. Connected analysis is capable of revealing relationships between people who are otherwise acting like perfect strangers.
3. e-Commerce Fraud: As our lives become increasingly digital, a growing number of financial transactions are conducted online. Fraudsters have been quick to adapt to this trend, and to devise clever ways to defraud online payment systems. While this type of activity involves criminal rings, a well-educated fraudster can create a very large number of synthetic identities on his own, and use these to carry on sizeable schemes. As in the first-party bank fraud, and insurance fraud examples above, graph databases are designed to carry out pattern discovery in real-time across precisely these kinds of data sets. By putting checks into place and associating them with the appropriate event triggers, such schemes can be uncovered before they are able to inflict significant damage.