Financial crime is connected.
Detection should be too.
RAQB is developing intelligent AML and financial crime technology that combines configurable detection methods, machine learning, and connected financial intelligence to help uncover complex suspicious activity.
Built in Kuwait. Designed for financial institutions.
Rules detect known patterns.
Financial crime also moves across relationships.
Suspicious activity rarely sits in a single transaction. It can emerge through sequences of transfers, related accounts, entities, and behavioral patterns that become meaningful only when they are read together.
Rules & Scenarios
Rules, thresholds, and scenarios provide an essential foundation for detecting known suspicious patterns.
- Institution-defined risk conditions
- Transparent, explainable logic
- Established regulatory practice
Relationships & Behavior
RAQB extends traditional monitoring by analyzing behavioral and relational signals across transactions and entities.
- Behavior analyzed across linked entities
- Patterns read from the wider structure
- Additional risk context for investigators
An essential foundation: known patterns checked against defined thresholds and scenarios.
RAQB extends that foundation, reading signals together so potential suspicious patterns become visible earlier.
Understand the network, not just the transaction.
RAQB combines rules and scenarios, machine learning, and connected intelligence as complementary layers. Together they produce richer risk context, while investigation and decisions remain with the analyst.
- Rules & Scenarios
Known patterns and institution-defined risk conditions are detected.
- Machine Learning
Unusual behavioral patterns and emerging risk signals are identified.
- Connected Intelligence
Relationships across transactions, accounts, customers, and entities are analyzed.
- Investigation Context
Risk context is assembled to support the investigator.
Turning financial crime research into technology.
RAQB translates financial crime research into practical detection capabilities designed for real financial environments, exploring how advances in machine learning, graph intelligence, and financial crime analytics can be applied in practice.
Financial crime, AML, and network research
Machine learning, graph, and hypergraph methods
Detection and investigation capabilities
Designed for institution-controlled environments
Research and production remain clearly distinguishable: experimental models inform our development direction, while capabilities are validated before they are proposed for use in a financial environment.
A new intelligence layer for financial crime teams.
Identify suspicious activity using configurable detection methods and intelligent risk signals.
Analyze relationships across transactions, accounts, customers, and entities to reveal patterns that may be difficult to identify in isolation.
Provide investigators with relevant risk indicators, relationships, and context to support informed investigation.
RAQB is exploring AI-assisted investigation capabilities designed to help analysts understand alerts, review relevant relationships, summarize activity, and organize investigation context.
AI supports the investigation process. Final decisions remain with authorized investigators.
Built around connected financial data.
Explore behavioral patterns and identify risk signals beyond predefined scenarios.
Analyze relationships between transactions, accounts, customers, and related entities.
Research higher-order financial relationships where suspicious activity may involve multiple interconnected entities and interactions.
These technologies enable RAQB's capabilities rather than being the product themselves. They are intended to complement traditional AML monitoring, with detection strategies configured according to institutional risk requirements.
Research shouldn't stop at publication.
RAQB explores how advances in machine learning, graph intelligence, and financial crime analytics can be translated from research into practical detection capabilities.
Take promising financial crime research and turn it into technology that institutions can actually use.
Building financial crime intelligence from Kuwait for the region.
RAQB is being developed with the requirements and operating environments of financial institutions in Kuwait and the wider region in mind, and designed to support deployment within institution-controlled environments.
Research-driven. Industry-focused.
RAQB is a Kuwait-based RegTech venture focused on developing intelligent technology for anti-money laundering and financial crime detection.
Our work combines financial crime research, machine learning, graph-based intelligence, and practical software development, with the goal of translating advanced research into capabilities that can support real financial institutions.
Interested in what we're building?
Whether you're a financial institution, researcher, industry expert, or potential partner, we'd like to hear from you.