E-commerce fraud detection with graph technology

August 9, 2017

E-commerce fraud is growing quickly, creating new challenges in prevention and detection. The key element in the fight against fraud is now to draw on the connections within the data collected about customers, transactions and behaviors, to uncover fraudulent behaviors. In this article, we'll explain how to accelerate e-commerce fraud investigations with graph technologies like Linkurious Enterprise.

E-commerce: a fertile ground for fraud

In recent years, the e-commerce market has greatly expanded, reaching $1.9 trillion in transaction value in 2016. E-commerce sales are still growing rapidly and are forecast to reach $4 trillion by the end of 2020, notably with retailers pushing into new international markets.

In the meantime, e-commerce fraud has become a multi-billion dollar industry for criminals. A study conducted by Juniper estimated the average cost for merchants between 0.3% and 3% of revenues depending on the vertical and the region. Below are some examples of today’s most common fraud schemes.

eCommerce fraud types

The adoption of new technologies, payment methods, and data processing systems has benefited fraudsters. New technologies have opened doors for them to bypass existing security measures and cover their tracks. Fraudsters have also become professionalized, working in organized networks. They exchange knowledge and technology across the globe and devise new schemes to stay one step ahead of the latest anti-fraud technology.

A layered approach to fight the rising challenges of e-commerce fraud

E-commerce merchants need to adapt to new fraud tactics. They are faced with increasing flows of money and evolving fraud schemes, but also with new technology disrupting traditional security measures.

The traditional “silver bullet” approach of relying on one or two anti-fraud strategies is no longer enough. Best in class organizations combine multiple complementary approaches to maximize the accuracy of fraud detection and avoid false positives that negatively impact reputations. With numerous fraud prevention solutions available — from device authentication to proxy piercing, or address verification service — the layered approach shows better results in detecting fraud attempts.

In their Market Guide for Online Fraud Detection, Gartner’s fraud analysts outlined five critical layers to tackle today’s threats: end-point, navigation, channel and cross-channel centric layers and an additional entity link analysis layer.

e-commerce fraud detection
Gartner’s conceptual model of a layered approach for fraud detection

In order to carry out connected analysis, e-commerce vendors need technologies able to work with cross-channel data and performing relationship analysis at scale. However, most of today’s anti-fraud solutions (whether it’s homemade or provided by a vendor) still rely on relational databases, designed to store data in a tabular format. Detecting connections between entities becomes computationally intractable after a few hops.

As a result, e-commerce fraud detection teams are still limited by product and channel silos that provide little or no cross-channel view of a subject’s behavior. Existing structures are too rigid to allow the easy adoption of new rules or data, making it hard to keep pace with new products and schemes.

Graph technology: the answer for connected fraud analysis

To be able to perform connected analysis and reinforce their fraud detection system, e-commerce merchants are turning to graph technology. This approach relies on a graph data model where all the data is stored as a graph. Individual entities are stored as nodes, connected to each other by edges. Popular graph databases vendors include Cosmos DB and Neo4j.

Graph technology lets you gather and connect customer, transaction, behavior or third party data into a unique data model. This is essential to discover e-commerce fraud attempts that are often hidden beyond layers of deceit. For instance, instead of examining credit card transactions over a period of time, analysts can query the graph data to investigate how it’s connected to other entities such as IP addresses, customers, devices.

Linkurious graph visualization
Visualization in Linkurious of cross-channel data stored as a graph in Neo4j

The graph approach is ideal to query connections within the data. Anti-fraud teams can run queries traversing datasets of millions of records to unveil suspicious connections. This is critical to detect networks and suspicious patterns in real-time. But in order to speed up the analysis process, and therefore the response time, e-commerce merchants need intuitive accesses to this graph data. 


Linkurious helps e-commerce fraud detection teams leverage graph databases’ abilities with a fraud investigation platform.

E-commerce fraud detection with Linkurious Enterprise

To illustrate what fraud detection analysis with Linkurious Enterprise looks like, we created a small dataset with dummy data and loaded it into a graph database. In the following sections, we explain how anti-fraud teams can leverage Linkurious Enterprise to detect and investigate fraud attempts.

Setting up alerts to monitor fraud attempts

As new fraud schemes emerge, the ability to create detection rules on the fly is critical. Graph traversal languages, such as Cypher or Gremlin are simple yet complete enough to let analysts imagine new queries that will flag fraudulent behaviors. Linkurious Enterprise offers an alert dashboard to generate and monitor different alerts and assess flagged cases.

For instance, we want to set up an alert query that returns any transactions that have a connection with at-risk countries. The list of these countries is integrated into the graph model and appears as a property on our country nodes. The data is processed in near-real time and you get an immediate response of whether or not there are such patterns in your data.

Fraud detection Linkurious
Setting up alerts in Linkurious using Cypher query language

The above alert will flag transactions where the IP or delivery addresses is located in one of the countries on my “at-risk countries” list. For every case reported, a team can visually investigate the data in Linkurious Enterprise.

Visually investigating graph data

Whether it’s to investigate specific alert cases or learn more about a particular entity, analysts can easily search and visualize their data in real time in the Linkurious Enterprise interface. For instance, we can generate a visualization compiling a subset of transactions and their related connections with a simple query. Below is the visualization of our subset of transactions (red nodes), the associated credit cards (blue nodes) and customer accounts (green nodes). We see that nodes are connected together, depicting the ownership relationships between credit cards and customers.

Transactions visualizations for e-commerce fraud detection
Example of visualization of graph data nodes (customer, credit card and transactions) and their connections

By using different graph layouts, we can easily reveal structural patterns in the data to identify differences in a glimpse. In the example below, we switched from a force-directed layout to a hierarchical layout in order to better understand the different cases we have.


e-commerce fraud detection in Linkurious Enterprise
Visualization with a hierarchical layout of a subset of transactions and their related nodes

We immediately notice a suspicious pattern in the graph. Customers (green nodes) are typically connected to a single credit card (blue node) which is connected to one or several transactions (red nodes). But there’s one case where two green nodes (two customers), are connected to the same credit card which is suspicious.


It is easy to drill down on a suspicious case with the Linkurious Enterprise interface. Analysts simply expand the nodes around suspicious patterns to reveal other connections within the data and assess the situation. In our example, we expanded the nodes around our two customers and the transactions to unveil a sub-graph with additional information (customer IP addresses, contact information, addresses, goods bought and shipping addresses).

e-commerce fraud detection in Linkurious Enterprise
Investigation of the neighboring nodes of our suspicious customers

With this visualization, we understand that actually three users are involved. Two of them, from different countries, ordered goods and shipped them to a third client, which could indicate a reshipping fraud.

Linkurious graph technology offers an additional layer of protection for e-commerce fraud detection. It enhances discrete analysis methods by providing connected analysis capabilities over a single source of truth of customer data. With Linkurious Enterprise, anti-fraud teams have an intuitive tool to detect and investigate fraud attempts and fraud rings that would otherwise stay undetected.

See Linkurious Enterprise in action
Subscribe to our newsletter

A spotlight on graph technology directly in your inbox.