Know what you don’t know

Data visualization techniques help analysts quickly uncover patterns and trends

By Jason Grasso, Solutions Architect, SAS Security Intelligence Practice

Risk professionals are always concerned about the “known, unknown and unknowable.”  The next question is how do you start to know what you don’t know? The anti-money laundering (AML) scenarios and automated detection methods employed by most firms are covering off on the risk typologies that they are already aware of. How do we go about identifying new or emerging typologies that are not already covered?

More proactive firms who understand that reputation risk is at stake every day are looking for emerging risks. Given the amount of data and transactions that firms handle it’s not easy to sift through spreadsheets or alert queues to detect these anomalies. By leveraging in-memory technologies, data visualization allows investigators to scan large amounts of data through graphs, decision trees and other methods to identify potentially anomalistic patterns or relationships. From there investigators can drill into the information and determine if this is truly a risk. If so, further analysis can be done to determine the extent of the risk and determine if this risk typology needs to be put into production through AML scenarios.

As threats become more complex, the need for a quicker, easier way to uncover the risk is more and more important.

And as threats become more complex, the need for a quicker, easier way to uncover the risk is more and more important. Data visualization –through entity networks, heat maps or other spatial representations – is a better way to first identify the extent of the risk rather than using cross tabular analysis. Especially, when dealing with very large volumes of data, data visualization techniques can show the user whether an event is an outlier or possibly part of a more complex pattern of risk exposure.

In-memory data visualization allows the analyst or data scientist the flexibility to analyze data at different dimensions, such as book of business, geography, or account-level behaviors. For example, large spikes in product utilization, flow of funds between geographies and industry analysis can be used to ensure that the automated detection methods have properly covered these risks. This approach allows AML business users to be more self-sufficient and not rely on other parts of the firm to provide data for analysis and exploration.

With the ever changing geopolitical landscape and ever increasing regulatory pressures, firms are exploiting new data visualization technologies to provide proper oversight to manage the unknown. Read this free white paper to learn how you can use predictive analytics to pinpoint suspicious activity.


man looking out of window

Read More

Read this free white paper to learn how you can use predictive analytics to pinpoint suspicious activity.

Get More Insights

iPad

Want more Insights from SAS? Subscribe to our Insights newsletter. Or check back often to get more insights on the topics you care about, including analytics, big data, data management, marketing, and risk & fraud.

Back to Top