No results found

Your search did not match any results.

We suggest you try the following to help find what you’re looking for:

  • Check the spelling of your keyword search.
  • Use synonyms for the keyword you typed, for example, try “application” instead of “software.”
  • Try one of the popular searches shown below.
  • Start a new search.
Trending Questions

Imagine a Smarter, Risk-Based Approach to Financial Crime and Compliance Management

It’s easy to understand how financial services firms can feel like they’re losing ground in their efforts to defend against financial crime. Schemes are increasingly sophisticated, and, while detection solutions have advanced, they often result in a flood of false positives and still require significant manual intervention. The result: financial crime and compliance management (FCCM) programs that are inefficient, expensive, and largely unsustainable as threats and requirements grow.

Among the most challenging aspects of instituting effective anti-money laundering (PDF) and anti-fraud programs at financial institutions is the need to adapt quickly to changing patterns of financial crime to limit both financial and reputational risks. Institutions must work unceasingly to create more accurate models to catch ever-more sophisticated illegal activity, reduce the cost of investigating false positives, and protect client relationships.

As a first line of defense, many financial institutions rely almost exclusively on a series of rules-based solutions, which cannot keep pace with the highly dynamic nature of financial crime today; nor can they deliver the immediate insight and predictive intelligence that can enable firms to actually stay one step ahead of the criminals instead of paces behind. In addition, siloed legacy solutions prevent a best-practice enterprise-wide approach to financial crime detection that significantly reduces risk.

With more innovative products and data sources than ever, the ability to continually discover emerging risks and new criminal patterns, coupled with the capacity to rapidly operationalize newly developed models into production, is a necessary requirement for modern financial crime platforms. In this environment, firms look to embrace graph analytics and machine learning to drive a smarter, risked-based approach to FCCM.

Purpose-Built for the Detection of Financial Crime

As false positive reduction continues to be the priority for financial institutions, a judicious combination of advanced techniques, such as financial networks visualization, transaction flow analytics, and machine learning must be at the disposal of financial crimes data scientists. Further, financial crime and compliance management business and operational teams—from investigators to scenario testers—need tools to help them quickly understand, digest, and act upon the findings produced by the data scientists.

Oracle Financial Services Crime and Compliance Studio meets the needs of all these diverse groups. It is an integrated workbench for financial crime data scientists and compliance risk coverage analysts, providing a comprehensive analytics toolkit along with secure access to the institution’s financial crime data. It is designed from the ground up to enable data scientists to rapidly discover and model financial crime patterns and quickly share their findings graphically with non-technical business partners and customers. With seamless access to production data in a secure and isolated discovery sandbox and predefined scenarios, institutions gain an accelerated path to interactively explore financial crimes data.

Portal into the Financial Crimes Data Lake

Effective discovery requires all financial institution transactions, accounts, alerts, and other financial crimes-related data, such as watch lists and datasets from the International Consortium of Investigative Journalists, to be brought into an analytical data lake. All of this data is linked together and made available for discovery and analysis with Oracle Financial Services Crime and Compliance Studio.

Engineered to be a portal into the enterprise’s financial crimes data lake, Oracle Financial Services Crime and Compliance Studio includes an industry-first data model for graph analytics across financial crime data. The included Enterprise Financial Crimes Graph Model (EFCGM) provides a target representation for the data lake data as an enterprise-wide global graph, enabling a whole new set of financial crime use cases. The global graph, therefore, links all of the institution’s financial crimes data —anti-money laundering (AML), fraud, alerts, sanctions lists, know your customer (KYC) data, and external datasets—and serves as the single, central source for compliance investigations.

Additionally, in an environment where Oracle compliance applications are installed, Oracle Financial Services Crime and Compliance Studio automatically loads data from the Oracle Financial Crimes Data Model (PDF) into the data lake, significantly reducing the time and effort data scientists spend in preparing data for analysis.

Integrated Development Environment to Serve All Users

Effective criminal pattern discovery and detection requires the application of a variety of techniques and collaboration across multiple teams with various levels of technical expertise. Oracle Financial Services Crime and Compliance Studio provides a single, unified workbench for graph analytics, data visualization, machine learning, and scenario authoring and testing for financial crime data.

  • Oracle Parallel Graph Analytics: Succinctly express complex money movement patterns, detect multihop relationships, and identify hubs and spokes of activity using more than 30 supplied graph algorithms and a built-in, SQL-like query language.

    Oracle Financial Services Crime and Compliance Studio includes a highly scalable, in-memory graph analytics engine (Oracle PGX). All of these algorithms are made immediately usable because of the included EFCGM and accompanying notebooks.
  • In-Database and In-Cluster Machine Learning: Publish machine learning notebooks in R and Python. Use open-source packages in R, Python, Spark ML, or Oracle’s optimized libraries for machine learning, such as Oracle R Enterprise and Oracle Advanced Analytics for Hadoop.
  • Polyglot Scenario Authoring: Author and deploy new AML and fraud detection scenarios or test existing scenarios with what-if analysis. Scenarios can be written in SQL, Scala, Python, or R.

Although Oracle Financial Crime and Compliance Studio makes complex analytics and visualizations more accessible to business users, it is nevertheless a tool more suited for the technical user—data scientists, scenario authors, and technically minded compliance risk coverage analysts. These users serve as the primary content authors within the studio environment. Consumption of this content in business applications is enabled using the built-in publishing framework. Models, scenarios, graph visualizations, and other results can be consumed in applications such as enterprise case management or operationalized in production batches.

Leverage Existing Infrastructure Investments

Apache Zeppelin and Jupyter notebooks are the de facto standard development tools for data scientists; Apache Spark is the most prevalent analytics engine on big data. Oracle Financial Services Crime and Compliance Studio leverages these open technologies and standards, thereby minimizing the need to retrain data scientists. Furthermore, the ability to use popular data science languages, such as R, Python, SQL, and Scala, serves to increase modeler productivity. Oracle Financial Services Crime and Compliance Studio is also tested with leading distributions of open-source Apache Hadoop and Apache Spark, enabling quick integration with existing data lake infrastructure technology.

Oracle Financial Services Crime and Compliance Studio is engineered to work with earlier 8.x releases of Oracle Financial Crime and Compliance Management Anti-Money Laundering and Fraud applications, reducing the need to upgrade existing environments and reducing the overall cost.

For more information, view

Contact us:

Related Products and Solutions

Graph Analytics and Machine Learning

A portal into the financial crimes data lake. Apply machine learning, advanced analytics, and automation to turn raw data into actionable intelligence.

Transaction Monitoring

Next-generation AML compliance tools to analyze and mine suspicious patterns and transactions.

Customer Screening

Advanced threat detection while minimizing false positives.

Transaction Filtering

Complete coverage of sanctions monitoring with detection, analysis, and resolution capabilities.


Discover More

Meeting the AML Challenge

Meeting the AML Challenge: A Response to Celent’s Report

Oracle identified seven key findings where advanced analytics can help financial institutions improve compliance programs and gain competitive advantages.

woman with credit card paying bartender with contactless payment

Addressing Financial Crime and Compliance Challenges with Advanced Analytics

Oracle explains some specific approaches and technologies that can help solve financial crime, compliance, and AML challenges.

solution to transaction monitoring

Network-Based Surveillance: A Solution to Transaction Monitoring

Oracle reviews the three challenges with traditional monitoring for financial crime, and shares the five benefits of network-based surveillance.