TigerGraph Selected to Strengthen Fraud Detection and Credit Risk Assessment
REDWOOD CITY, Calif., Nov. 20, 2019 – TigerGraph, the only scalable graph database for the enterprise, today announced that the world’s most innovative financial services organizations — from emerging companies to the world’s largest banks — have selected TigerGraph to strengthen their fraud detection and credit risk assessment efforts. In fact, four of the five largest global banks and the world’s largest payment card provider use TigerGraph for their anti-fraud initiatives. These leading banks and other financial institutions are turning to TigerGraph’s graph analytics platform for their most critical tasks, as the technology is purpose-built for linking, analyzing and computing ML (machine learning) and AI algorithms and analyzing complex data.
“Financial services organizations are among the most powerful – yet vulnerable – institutions in the world. For every dollar of fraud, financial services companies incur $2.92 in costs, and this figure is on the rise. These organizations spend billions of dollars on anti-fraud efforts and employ thousands to uncover fraud,” said Dr. Yu Xu, CEO and founder of TigerGraph. “TigerGraph helps these companies improve their machine learning applications with graph analytics to improve the detection of ‘bad patterns’ within their vast amounts of data. If a credit applicant is a visitor knocking on your door, TigerGraph helps you see how many times they’ve knocked before, what information they have used and how this may compare with previously identified ‘bad applicants.’ TigerGraph completes all of this analysis in real-time. This allows the financial service organization to decide if you want to ‘open the door’ and do business with this person, enlist a human investigator to review the case, or decline the business as ‘high-risk.’”
In a February 2019 announcement, Gartner, Inc. identified graph as a Top 10 Data and Analytics Technology Trend for 2019 stating, “The application of graph processing and graph DBMSs will grow at 100 percent annually through 2022 to continuously accelerate data preparation and enable more complex and adaptive data science… Graph analytics will grow in the next few years due to the need to ask complex questions across complex data, which is not always practical or even possible at scale using SQL queries.” Graph database technology can analyze relationships in data to make pattern and similarity analysis stronger. For example, financial institutions are strengthening their machine learning and AI systems with graph database to visualize, analyze and detect complex data patterns – patterns that indicate the potential for fraud. A bank can apply “application attributed linking” to compare a known fraudulent credit/debit card application with a new credit card/debit card application; if and when shared attributes are detected within new applications, the bank can then reject those applications as fraudulent. This same “compare and reject” process can be applied to credit or debit card transactions as well.
Here’s how leading financial services organizations are implementing next-generation graph database technology and signing on with TigerGraph:
- A major U.S. financial services software company selected TigerGraph to power its payment fraud and investigation efforts. Fraud detection and prevention requires understanding connections and identifying anomalies in links between people, transactions, payment methods, locations, times and more — and working to do this within huge and often incomplete datasets. The company uses TigerGraph to visualize payment information, specifically the associated account, user and device information and all connections among them. After data is “visualized,” fraud investigators can analyze data to surface suspicious patterns and previously confirmed bad patterns can help locate new instances of fraud. Then, the technology examines billions of payments to find repeating fraudulent patterns throughout the data set. The offenders are flagged and the transactions stopped. Every time a payment is generated, it is checked in real time against multi-level patterns for potential fraud. Meanwhile, during this visualize-analyze-find/stop process, the system is learning; the machine learning becomes skilled at flagging future fraud patterns within the ever-changing data set. This computational learning and modeling improves current analytics algorithms, making the machine learning modules smarter and faster. As this entire cycle is automated, fraud investigators can use the results to better prioritize which cases they focus on.
- A leading U.S. multinational investment bank selected TigerGraph to improve its fraud avoidance initiatives, specifically fraud detection for debit and credit cards. The organization will add graph analytics to their machine learning system to find data connections between “known fraud” credit card applications and new applications. The result: the bank will identify questionable patterns, expose fraud rings and shut down fraudulent cards. Anticipated savings: millions of dollars annually.
- The world’s largest payment card provider will use TigerGraph as its main graph analytics platform for payment fraud detection and merchant credit management. The company, which had been using RDBMS (relational database management system), is now standardizing on TigerGraph’s scalable and secure graph database. Relational databases fall short in identifying patterns among disparate datasets. They are complex, slow and perform poorly when it comes to deep analytics. TigerGraph is purpose-built for deep pattern analytics and its real-time update capabilities are crucial for this financial services leader’s anti-fraud work.
- China Construction Bank (CCB), the world’s second largest bank, chose TigerGraph to support its next generation analytics platform at the Big Data Innovation Center. CCB, with TigerGraph, can analyze its vast data store – 18 terabytes and growing – for greater customer insight, anti-money laundering and credit fraud detection. Generating between five and six terabytes of transaction data every year, CCB has struggled to scale in the face of increasingly complex data and hundreds of millions of personal and corporate accounts from subsidiaries across the globe. CCB chose TigerGraph for its ability to analyze complex and connected data 10 layers deep to generate new patterns and algorithms to improve its fraud models. By signing CCB, TigerGraph has now won two of the top four commercial banks in China.
- Pagantis, a point of sale financing (POSF) platform for ecommerce in Europe, selected TigerGraph to speed up its real-time risk-scoring and fraud prevention processes and reduce customer wait times. The Spain-based fintech now offers a fast, seamless consumer finance solution with automated consumer credit for e-commerce transactions in Italy, France and Spain. Pagantis uses TigerGraph to calculate a customer’s credit rating using all of their real-time activities as well as historical context. Pagantis offers financing with instant online approval, carried out in real time through an innovative scoring algorithm. This algorithm analyzes the risk of fraud and credit to ensure the highest possible acceptance by controlling the risk of delinquency.
For more on TigerGraph’s graph database solutions and features, click here.
TigerGraph is the only scalable graph database for the enterprise. Based on the industry’s first Native and Parallel Graph technology, TigerGraph unleashes the power of interconnected data, offering organizations deeper insights and better outcomes. TigerGraph fulfills the true promise and benefits of the graph platform by tackling the toughest data challenges in real time, no matter how large or complex the dataset. TigerGraph’s proven technology supports applications such as fraud detection, customer 360, MDM, IoT, AI and machine learning to make sense of ever-changing big data, and is used by customers including Amgen, China Mobile, Intuit, Wish and Zillow. The company is headquartered in Redwood City, California, USA. Follow TigerGraph on Twitter at @TigerGraphDB or visit www.tigergraph.com.