UBO Identification in AML:
Why LLMs Fail & How Composite AI and AI Agents Get It Right
As global regulations tighten, the accurate identification of Ultimate Beneficial Owners (UBOs) has become a critical, yet error-prone compliance task. While many turned to AI, standard Large Language Models (LLMs) have proven inadequate for the analytical rigor required, highlighting a fundamental misuse of the technology. The solution lies in a more sophisticated, multi-layered approach combining graph technologies with Agentic AI to deliver the necessary accuracy, explainability, and automation.
If you're ready to move beyond theoretical discussions and see how Composite AI and AI Agents can transform your UBO identification workflows, request a live demo now and experience DataWalk in action. Discover how your compliance team can achieve faster, more accurate, and fully auditable UBO analysis.
The Regulatory Challenge of UBO Identification
Across the global financial landscape, identifying Ultimate Beneficial Owners (UBOs) is not optional-it's a regulatory imperative. Mandates from bodies like OFAC in the USA, coupled with the European Union's "50% or more" ownership threshold and the UK's stringent sanctions regime, demand not just compliance but full transparency and auditability in the ownership determination process. Despite this pressure, UBO analysis remains one of the most complex and labor-intensive tasks in financial compliance, frequently leading to the question heard at industry events like ACAMS Europe 2024: "How do you handle UBOs?"
ACCELERATE YOUR INVESTIGATIONS WITH PROVEN STRATEGIES AND LESSONS FROM REAL-WORLD SUCCESS STORIES.
Gain access to the DataWalk articles and case studies
For FinCrime Investigators
Gain access to the DataWalk articles and case studies for FinCrime Investigators
Gain access to the DataWalk articles and case studies for FinCrime Tech Professionals
Why Standard AI Fails: The Limitations of LLMs
Recent experiments with leading LLMs like ChatGPT, Gemini, and Copilot reveal a consistent pattern of failure when analyzing even moderately complex ownership structures. These models frequently make critical errors, including incorrect multiplication of ownership percentages across nested entities, failure to aggregate shares from sanctioned individuals, and drawing erroneous conclusions about sanction exposure. The root cause is not a failure of AI itself, but its misapplication. LLMs are designed for language generation, not procedural analytical reasoning. They lack the built-in logic to navigate complex ownership hierarchies and perform the precise calculations required for compliance.
Composite AI and AI Agent: The New Paradigm for Analytical Reasoning
A more effective approach is found in Composite AI — a unified architecture that combines multiple AI techniques to deliver intelligent, goal-oriented analysis. Within this architecture, Agentic AI components autonomously plan and execute multi-step reasoning tasks. They work with structured knowledge graphs and verified data, pursue clearly defined objectives (e.g., identify the UBO), and orchestrate workflows across other AI elements like LLMs and ML models. Most importantly, they generate transparent, human-readable insights that trace every step of the analysis, ensuring full auditability and explainability for regulators.
A Three-Step Process for UBO Automation
Effective UBO automation requires a structured, multi-layered process that breaks the challenge down into three manageable, technology-driven steps.
Step 1: Entity Resolution
Financial institutions often hold fragmented data across legacy systems. For example, one system may have a full company name, another just an email, and a third only a physical address. Before any analysis can occur, this data must be unified. Using an ontology-based knowledge graph, Entity Resolution technology synthesizes these disparate data points, inferring connections based on contextual clues to create a single, reliable view of each entity. This unified view is the non-negotiable foundation for accurate ownership analysis.
Learn More About DataWalk Entity Resolution
Step 2: Graph Inference
With a unified dataset, the next step is to reconstruct and analyze the ownership logic. Graph Inference algorithms traverse the knowledge graph to map ownership chains across multiple levels, calculate aggregated shares (including those from sanctioned entities), and automatically identify individuals or entities that surpass control thresholds. This technology is also uniquely capable of detecting anomalous structures designed to obfuscate ownership, such as circular dependencies or networks of entities holding small shares.
In standard systems built on relational databases, performing such deeply nested calculations is not straightforward — each additional ownership layer requires new joins and complex query logic that quickly becomes unmanageable at scale. The challenge becomes even more complicated when analysts need to answer time-related questions, such as who controlled a company in 2020. This demands the inclusion of temporal data to track when ownership started and ended. Only graph-native architectures handle this complexity efficiently, as they persist relationships and temporal attributes as part of the data model, making it possible to query historical control paths directly.
Step 3: Agentic AI Interpretation
The final layer is the Agentic AI interface, which acts as a decision-support system for compliance analysts. This agent interprets the findings from the graph inference step and allows users to ask natural language questions like, "Why is this entity flagged as high-risk?" The AI can then explain the logic chain ("Entity D, which is sanctioned, owns 26%, and Person X owns 25%; their combined control exceeds the 50% threshold."), visualize the ownership structure, and generate audit-ready documentation compliant with OFAC, EU, and UK standards.
DataWalk: Putting Composite AI and AI Agent into Practice
The principles of this three-step framework are embodied in the DataWalk platform. DataWalk provides a next-generation intelligence environment that operationalizes the Composite AI approach for complex compliance challenges like UBO identification:
- By integrating all data sources into a unified knowledge graph, DataWalk enables powerful Entity Resolution.
- Its advanced analytical engine performs sophisticated Graph Inference to uncover hidden ownership structures and calculate risk.
- Finally, its intuitive, user-centric interface empowers analysts to investigate, understand, and report on findings with the clarity and explainability that Agentic AI promises, turning a complex process into a manageable workflow.
Conclusion: The Future is Composite AI
DataWalk brings the principles of Composite AI into action through a clear, two-stage pipeline that supports complex compliance tasks such as Ultimate Beneficial Ownership (UBO) identification. First, all relevant data sources are connected and integrated into a unified knowledge graph, enabling robust Entity Resolution and advanced Graph Inference to reveal hidden ownership structures and risk relationships. Second, an Agentic AI layer interacts with these computed insights, empowering analysts to navigate findings, test hypotheses, and produce clear, defensible reports. This sequential pipeline makes Composite AI practical and explainable — turning what used to be a fragmented, manual process into a repeatable, auditable workflow.
Kamil Goral is an expert in developing advanced solutions for the DataWalk platform, specializing in areas critical to financial crime compliance such as cryptocurrency investigations, anti-money laundering (AML) and the application of AI/m achine learning.
ContactTable of contents
FAQ
When new questions arose, DataWalk's flexibility allowed for immediate exploration without disrupting the investigation flow. The platform's prototyping capabilities enabled the team to test new hypotheses quickly, link data from multiple sources in real-time, and discover previously unknown relationships between entities.
When new questions arose, DataWalk's flexibility allowed for immediate exploration without disrupting the investigation flow. The platform's prototyping capabilities enabled the team to test new hypotheses quickly, link data from multiple sources in real-time, and discover previously unknown relationships between entities.
When new questions arose, DataWalk's flexibility allowed for immediate exploration without disrupting the investigation flow. The platform's prototyping capabilities enabled the team to test new hypotheses quickly, link data from multiple sources in real-time, and discover previously unknown relationships between entities.
When new questions arose, DataWalk's flexibility allowed for immediate exploration without disrupting the investigation flow. The platform's prototyping capabilities enabled the team to test new hypotheses quickly, link data from multiple sources in real-time, and discover previously unknown relationships between entities.
When new questions arose, DataWalk's flexibility allowed for immediate exploration without disrupting the investigation flow. The platform's prototyping capabilities enabled the team to test new hypotheses quickly, link data from multiple sources in real-time, and discover previously unknown relationships between entities.
Composite AI in financial compliance means combining multiple specialized AI techniques to solve complex analytical tasks that traditional tools alone can’t handle. In DataWalk, this is implemented as a two-stage, sequential pipeline:
Graph Analytics Stage: Data from multiple sources is integrated into a unified knowledge graph. Graph analytics and inference techniques are used to resolve entities, map indirect ownership paths, and calculate risk scores. These operations run as calculated columns, virtual paths, or scheduled dependency refreshes in the core DataWalk engine — or can be executed on demand.
Agentic AI Stage: Once the graph is computed, an Agentic AI layer uses these results to drive further analysis and reporting. This could be done through user-triggered workflows, automated scripts (for example, in a Jupyter notebook), or custom in-platform applications that take the resolved graph and risk signals as inputs and produce auditable reports, alerts, or recommendations as outputs.
By combining these tasks into a clear, repeatable pipeline, Composite AI makes advanced compliance use cases — like Ultimate Beneficial Ownership (UBO) identification — manageable, explainable, and defensible.
Composite AI in financial compliance means combining multiple specialized AI techniques to solve complex analytical tasks that traditional tools alone can’t handle. In DataWalk, this is implemented as a two-stage, sequential pipeline:
Composite AI in financial compliance means combining multiple specialized AI techniques to solve complex analytical tasks that traditional tools alone can’t handle. In DataWalk, this is implemented as a two-stage, sequential pipeline:
Join the next generation of data-driven investigations:
Discover how your team can turn complexity into clarity fast.
Solutions
Product
Partners
Company
Resources
Quick Links