Case Studies

Ultimate Counter Parties

Top Japanese Bank Identifies Ultimate Counter Parties and Correlates Risk with Detection Model Rules


A top Japanese bank was lacking the ability to assess the risks associated with the ultimate originators and beneficiaries of the wire transactions that it processed and cleared. Unlike its regular customers, these entities were not being reviewed through any Know-Your-Customer (KYC) processes or any of the Customer Identification Programs (CIP). Further complicating matters of identifying these entities and ascertaining relevant information was the lack of standardized referential data and distinct identifiers.
The Matrix-IFS team developed a unique methodology to identify and classify the external originators and beneficiaries into risk-based categories using inconsistent data attributes and an automated process to parse high-risk geographic information from the wires’ free-form text. The team combined the risk of the entity with the risk of the domicile country in order to establish a risk score per wire transaction.



By aggregating the risked-based scores of the transactional activities, a risk profile was created for each of the external entities. Once the same methodology was applied to the transactions alerted by the detection scenario models, an enhanced risk-rating system was implemented so that the detection scenario models would produce a higher percentage of high-risk transaction wires, while the low-risk wire transactions would not be alerted.


As a result, false positive alerts were reduced by 40%.



Additional enhancements are being applied to both the entity classification process and transactional risk classification process to optimize tuning of the rules and increase the scrutiny on the higher risk wires while reducing scrutiny on the low risk wires to support the bank’s business growth and diversification.


Market Surveillance Solution

Regulator Implements Customized Actimize Market Surveillance Solution to Meet Unique Business Requirements


A U.S. government agency that regulates financial markets acquired NICE Actimize’s off-the-shelf solutions for surveillance of trading activities. The Regulator has several exchanges within its jurisdiction. Each Exchange has its own unique trading activity, products, trading firms, market participants and market data. The NICE Actimize out-of-the-box solutions are geared to a single firm’s activity within a single marketplace. The Regulator required an overview across multiple markets and analysis of large volumes of daily data feeds, all in a timely matter.
The Matrix-IFS team built custom surveillance models, monitoring activities across multiple exchanges and detecting four unique market abuse activities. The Matrix-IFS team translated the Regulator’s business requirements into functional and technical specifications, coded the logic of the different models, and designed and built customized interfaces to display the wide variety of data. Screens included interactive graphs to help users easily visualize large amounts of various data.


On the backend, the Matrix-IFS team designed and developed efficient data-loading and scheduling processes and optimized databases for storing large volumes of data. This optimization minimized the time of loading, processing and storing the data.  Matrix-IFS staff also trained the Regulator’s staff on maintaining and enhancing the system for future enhancements and model development.



The Regulator now has an automated surveillance detection system generating quality findings. The loading, processing and storing of the large data files are performed in a reasonable  time allowing the Regulator to review results shortly after trading activity has occurred. Also, by utilizing the NICE Actimize Enterprise Risk Case Management (ERCM) solution , the Regulator has an audit tool to track and log open issues during the escalation workflow and until resolution.



The Regulator plans to leverage the existing platform and add additional surveillance detection models along with incorporating additional Exchanges.


Top U.S. Bank Improves Quality

Top U.S. Bank Improves Quality of Real-time Fraud Monitoring Alerts While Cutting Process Time in Half

A top U.S. bank was receiving an unmanageable amount of alerts with various degrees of quality from its real-time fraud monitoring system. Data quality issues were difficult to detect and long data processing times were hindering the ability to effectively monitor fraud in real-time, exposing the bank to increased risks from fraudulent activities.


Data quality issues were difficult to detect, and long data processing times were hindering the ability to effectively monitor fraud in real-time, exposing the bank to increased risks from fraudulent activities.

The Matrix-IFS team developed and implemented an automated data-validation tool to better detect anomalies, errors and omissions in the data fed into the surveillance system. Using database performance diagnostic tools, the team analyzed the data loading and manipulation processes to more accurately identify and resolve ‘bottlenecks’ and other inefficiencies.



Using the data validation tool, some 10,000 unique semantic issues and over 25,000 syntactical constraint errors were immediately identified. Resolving the issues and errors substantially reduced the number of false-positive alerts generated, which led to a more manageable amount of higher-quality alerts. The ongoing data validation process put in place by the Matrix-IFS team ensures that the data quality will remain high by detecting and alerting on any issues. System optimization and fine tuning reduced data record reading time from approximately 400 milliseconds to 200 milliseconds, allowing for a more effective monitoring capability and reducing the bank’s risks from fraudulent activities.



Building upon success, the Matrix-IFS team is implementing further system enhancements, including an extensive management reporting tool to accurately track the workflow activities of generated alerts. Also in development, a tool that can automate the unit testing of individual fraud detection rules for more efficient and effective future implementations of fraud detection models.