How to Uncover a Money Laundering Network in 7 Steps

Accelerating AML/CFT Investigations with Decision Intelligence

Introduction

The scale and scope of money laundering today is staggering. An estimated 2% to 5% of global GDP, or roughly €715 billion to €1.87 trillion, is laundered each year.

2-5% of global GDP

€1.9T estimated to be laundered each year

Despite intensive efforts by financial intelligence units (FIUs) and law enforcement authorities, these organizations succeed in stopping only an extremely small share of money laundering activities.

In the Netherlands, for example, the FIU-Nederland, police and prosecutor's office are flooded by a million suspected money laundering cases every year, far exceeding their capacity to investigate and prosecute perpetrators.

In 2021, the FIU-Nederland was notified of €15.4 billion worth of possible criminal transactions. Of this enormous amount, the FIU was able to seize only €386 million - a mere 2.5% share of suspected laundered funds.

To more effectively detect and prevent money laundering and terror financing, authorities require more powerful, technology-based solutions.

Combating Money Laundering in the Netherlands

1m Suspected money laundering cases annually

€15.4bn Estimated funds laundered annually

€386m Seized by FIU (2.5%)

AML Investigation Challenges

The traditional approach to combatting money laundering focuses on compliance. Financial institutions conduct Know Your Customer (KYC) and customer due diligence processes, which generate millions of Suspicious Transaction Reports (STRs) and Suspicious Activity Reports (SARs) and tend to produce many false positive alerts. This creates an information overload for the FIUs responsible for uncovering money laundering networks. The percentage of false positive alerts generated by traditional, rule-based AML/CFT tools is shockingly high, accounting for 90-95% of all suspicious transaction alerts.

Data Challenges

• Massive amounts of data from SAR/STRs
• Data siloed between multiple databases
• Little time to investigate each lead
• Noise generated from false positives

Decision Challenges

• Which STRs/SARs to focus on
• Which companies or individuals to focus on
• How to allocate and optimize investigation manpower and resources

Decision Intelligence Platforms for AML Investigations

Decision Intelligence platforms leverage technologies such as data fusion, machine learning and AI, in addition to collaboration and data visualization tools. These platforms enable organizations to automatically collect, fuse and analyze data from virtually any source, on a massive scale, in order to generate data-driven insights and decisions. This allows AML investigative teams to detect anomalies, identify patterns of suspicious activities, assess risks, and uncover new leads. Best-in-class Decision Intelligence platforms enhances data science with domain expertise, by allowing non-technical-domain experts to contribute their field-specific knowledge to the building of organization-specific analytical models.

Taking a Decision Intelligence Approach in AML Investigations

Decision Intelligence is the practical application of analytics, machine learning and AI technologies to augment and improve human decision making. Applying a Decision Intelligence approach allows AML investigative teams to detect money laundering networks more effectively and uncover the financial entities enabling them. Rather than looking at one transaction surfaced by a business rule, investigators would look at a full sequence of events, extracted from multiple data sources, within a chronological, geographical, and situational context. For example, rather than simply seeing the details of a suspicious financial transaction, an investigator could receive an alert about suspicious indicators, such as:

• Account has been dormant for two years
• Account beneficiary has a low credit score
• Company has 5 accounts located in 3 countries
• Account beneficiary signs for 8 separate companies

With the holistic view, detailed context and machine learning based risk scoring provided by decision intelligence platforms, investigators can focus on the highest priority transactions, construct a full investigation narrative, and accelerate their analysis in order to resolve cases faster.

Traditional approach

• Limited, disconnected data sources
• Focused on transactions
• Linear, binary narratives

Decision Intelligence approach

• Multiple, diverse data sources
• Focused on highest risk entities
• Connections based on context
• Uncover previously hidden links
• Draw map of events & construct full narrative

7 Key Steps in AML Investigations

Mapping the enabler network is a particularly effective approach to uncovering a money laundering operation. There are 7 key steps that can help investigators do so faster and more effectively.

Setting Up For Success

1. Fuse Data into a Holistic View
2. Define How Data is Presented

Mapping Enabler Network

3. Surface Suspicious Transactions With automated rules & alerts
4. Prioritize Leads To Investigate With ML-based risk scoring
5. Detect Suspicious Activities By correlating profiles
6. Construct The Narrative With AI-powered enrichment
7. Map The Network Using link analysis

Use Case Scenario

Using an illustrative scenario, we will explain the key steps and how a Decision Intelligence platform is vital to carrying them out. Read on to learn more.

Steps 1 and 2 are critical actions for organizations to lay the groundwork before an investigation starts, which need only be done once. Without the right decision intelligence platform in place, AML investigators will be overwhelmed with unusable data, and it will be difficult for them to make fast, high-quality decisions.

Steps 3 through 7 are the key stages for an investigator to follow from the moment an STR/ SAR comes in, or suspicious activity is detected, until the enabler network is mapped.

Step 1: Fuse Data into a Holistic View

A best-in-class Decision Intelligence platform fuses all available data sources, no matter the format or type, to provide a single, unified view for the entire organization. By connecting financial data with other structured and unstructured data, such as travel itineraries, shipping manifests, tax filings, invoices, company registries, and more, investigators can gain a deep understanding of individuals and entities involved in transactions. Otherwise, investigators are left to manually piece together a complete view of the investigation, wasting time and resources that could be directed to critical, high-value investigative tasks.

Step 2: Define How Information is Presented & the Data Model

AML investigators are confronted by a sea of data. A solution which is optimized for AML investigations and provides intuitive dashboards and widgets can save significant time, accelerate investigation workflows, and surface data that might otherwise be missed. Moreover, best-in-class Decision Intelligence platforms enable organizations to modify the platform's data model independently, with zero coding needed. This allows organizations to leverage the expertise of their veteran investigators and ensure that the platform best fits their organization's data sources and investigative methodologies.

Step 3: Surface Suspicious Transactions with Automated Rules & Alerts

Best-in-class Decision Intelligence platforms provide automated intelligence rules and alerts that can easily be defined by an investigator for each investigation. The capability to create automated rules and alerts is critical, as it proactively pushes crucial information to the investigator, significantly minimizing the risk that important information is not overlooked, and minimizing the need for time-consuming manual searches.

Use Case Scenario

To catch sanctions evaders, the investigator defines an intelligence rule to surface high-risk transactions:

• High probability nominee director being used to obscure ultimate beneficiary owner
• Total aggregate sum of transactions in last 7 days > €20,000
• Financial entity related to criminal activity

Step 4: Prioritize Leads to Investigate with ML-Based Risk Scoring

With thousands of STRs and SARs coming in daily, the most important decision facing an investigator is which STR/SAR to focus on, and which leads to follow. A Decision Intelligence platform calculates machine learning based risk scores for all relevant financial entities such as accounts, individuals, and companies, based on information from diverse data sources, which allows investigators to better prioritize their work.

Use Case Scenario

Automatic risk scoring surfaces an individual, Jonas Meyer, with suspicious indicators:

• Signing for >5 companies
• Inconsistencies in the individual's profile
• Carrying out large transactions

Step 5: Detect Suspicious Activities by Correlating Profiles

The ability to correlate entity profiles, such as individuals, accounts, companies, trusts and transactions, helps investigators to surface suspicious patterns and activities. Conducting this analysis manually on a mass scale would be virtually impossible. Any flagged inconsistencies or anomalies automatically increase the risk scores of the relevant entities.

Use Case Scenario

Related entities flagged as suspicious due to:

• Mismatch between Jonas Meyer's geographic location and locations of companies signed for
• Mismatch between transaction's stated purpose and company's industry classification

Step 6: Construct the Narrative with AI-Powered Enrichment

AI-powered content enrichment tools, such as textual, image, video and audio analytics, allow investigators to uncover and gather information from potentially valuable unstructured sources, such as adverse news reports and social media. This contextual information helps investigators construct the narrative of an investigation, by deepening their understanding of individuals, financial entities, methods of operation and corporate ties involved in suspected money laundering cases. Data from unstructured sources is crucial, as it enriches entity profiles, and augments risk scoring.

Use Case Scenario

Text analytics reveals links from Jonas Meyer to another company accused of bribery.

A subsidiary of the commodity trader Pelba Inc has pleaded guilty in a London court to seven counts of bribery related to its oil operations in several African countries.

The Serious Fraud Office, which had brought charges against the FTSE 100-listed company after conducting an investigation, said the sentencing hearing would take place on 2 and 3 November.

Last month, Pelba Inc said it would pay a $1.1bn (£900m) US settlement, and indicated it would plead guilty in the UK. The SFO had formally charged the company at Westminster magistrates' court in London with bribery offences for preferential access to oil between 2011 and 2016. The case was subsequently sent to the higher Southwark crown court for Tuesday's plea hearing.

The SFO said on Tuesday: "Pelba Inc Energy (UK) Ltd has today been convicted on all charges of bribery brought against it by the Serious Fraud Office. At Southwark crown court, the company admitted to multiple counts of paying bribes to secure access to oil and generate illicit profit.

Step 7: Map the Network using Link Analysis

Visual link analysis is a powerful capability that enables investigators to validate their analysis and map out the full operation and enabler network, allowing them to not only block a transaction but to also initiate AML enforcement measures. Using visual link analysis, investigators can trace several levels of relations to identify hidden links between financial entities, can follow the money trail by visualizing money flows and can more easily identify beneficiary owners.

Use Case Scenario

Using link analysis, the investigator discovers an additional company linked to Jonas Meyer has conducted a transaction with a politically connected businessman, who is on a sanction evaders list.

Transaction is blocked and network reported to law enforcement.

NEXYTE Decision Intelligence Platform

NEXYTE, Cognyte's Decision Intelligence Platform, is designed to accelerate decision-making and boost financial investigations through multi-source data fusion and machine learning analytics. NEXYTE enables authorities to significantly improve the accuracy and effectiveness of their investigations and risk assessment, leading to faster case resolution and increased recovery of illicit funds.

SOURCES

• KYC data
• STRs / SARs
• Sanctions lists
• Crypto transactions
• Open source

INSIGHTS

• Risk scoring
• Pattern anomalies
• Money trails
• Fraud detection

Learn more about NEXYTE

Website

Read about the benefits of NEXYTE for financial investigations >>

Demo

Request a demo >>

About Cognyte

Cognyte is the global leader in investigative analytics software that empowers a variety of government and other organizations with Actionable Intelligence for a Safer World™

Use of these products or certain features may be subject to applicable legal regulation. The user should familiarize itself with any applicable restrictions before use. These products are intended only for lawful uses by legally authorized users. Not all features may be available in all jurisdictions and not all functionalities may be available in all configurations.

Unauthorized use, duplication, or modification of this document in whole or in part without the prior written consent of Cognyte Software Ltd. is strictly prohibited. By providing this document, Cognyte Software Ltd. is not making any representations regarding the correctness or completeness of its contents and reserves the right to alter this document at any time without notice. Features listed in this document are subject to change. Contact your Cognyte representative for current product features and specifications. All marks referenced herein with the ® or TM symbol are registered trademarks or trademarks of Cognyte Software Ltd. or its subsidiaries. All other marks are trademarks of their respective owners.

© 2023 Cognyte Software Ltd. All rights reserved worldwide.

Footnotes:

1. United Nations Office on Drugs and Crime (UNODC)
2. www.dutchnews.nl, Oct. 2022
3. www.dutchnews.nl, Oct. 2022
4. Saaradeey, Ghosh, Ray, Ganesan & Rajagopalan, 2019