Compliance & Financial Crime
Anti-money laundering, regulatory compliance, financial crime detection, and risk management.
Not sure where to start? Take the 2-minute diagnostic to be placed into a learning mode tuned to your level.
Take the quiz →🧠 Concepts (15)
📚 Learning Paths (6)
KYC/CDD Workflows: From Onboarding to Ongoing Monitoring
Deep-dive into Know Your Customer and Customer Due Diligence processes — the frontline defense again
SAR Filing Scenarios: Identifying and Reporting Suspicious Activity
Master the art of Suspicious Activity Report writing through real-world scenarios — structuring, lay
Sanctions Screening: Tools, Techniques, and Compliance Challenges
Navigate the complex landscape of sanctions compliance — OFAC SDN lists, screening technologies, and
Money Laundering Typologies: Current Methods and 2026 Trends
Money launderers continuously adapt their methods to exploit gaps in regulatory frameworks. This mod
The Risk-Based Approach in AML: Framework, Calibration, and Implementation
The risk-based approach (RBA) is the cornerstone of modern AML compliance, requiring institutions to
Enhanced Due Diligence, PEP Screening, and Adverse Media in Practice
Enhanced Due Diligence (EDD) applies additional scrutiny to high-risk customers beyond standard KYC/
All Articles
Impression Share Prediction: An Offline Evaluation Task for Ranking Systems
Offline evaluation is a major gateway before online evaluation of ranking models in A/B testing. Standard offline metrics measure predictive accuracy, but are only a surrogate for downstream utility:
The New Mathematics of Democracy
This article surveys emerging directions in the mathematics of democracy. It uses three case studies --- voting theory, participatory budgeting, and deliberative democracy --- to highlight how contemp
ECO-ID: Event-Camera based Optical System for Secure Multi-User Ultra-Low Latency Identification
Time-critical interactive systems increasingly require ultra-low-latency device identification for multiple users, yet prevailing approaches such as passwords, QR codes, and RFID/NFC are constrained b
zLend: A Dual-Scope Cash-Flow Reconstruction Framework for On-Chain Credit Underwriting
Decentralized lending lacks a credit bureau: a borrower's capacity to repay must be inferred entirely from public on-chain activity, without income verification or a liability record. This paper prese
When ratios fall: A dynamic approach to contingent convertibles
We propose a novel valuation framework for contingent convertible (CoCo) bonds based on the issuing bank's Common Equity Tier 1 (CET1) ratio, which is widely acknowledged as an indicator of a bank's s
Sample Complexity of Peer Prediction
Peer prediction seeks to incentivize agents to truthfully report an observed signal by rewarding joint sets of reports without observing a ground truth. Following the generalization of information-the
GEO-Flag: Detecting and Measuring GEO-Optimized Web Content
Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized pages visibility di
UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation
Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior his
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typica
"This Is So Claude!" Towards a Theory of the Recognition of AI Character Without Reidentification
Users sometimes judge that an unfamiliar response is "so Claude." What does this judgment recognize, if it does not identify which model, process, conversation, or mind produced the response? I distin
A Deployment-Oriented and Resource-Efficient Neuro-Symbolic Framework for Explainable DDoS Detection in Operational Technology Networks
Operational technology (OT) environments, including programmable logic controllers (PLCs), industrial control systems (ICS), and supervisory control and data acquisition (SCADA) systems, are increasin
Rough Volatility Across Assets
We measure volatility roughness across asset classes using a common data infrastructure and pipeline. Our data covers 3,926 United States equities, 34 CME futures roots, rates, FX, and commodities, an
Liquid democracy under vote correlation: On the fallacies of averaging and the excluded middle
Liquid democracy permits voters to vote directly or delegate their votes to others. Existing algorithmic analyses assign each voter a single scalar parameter, interpreted as an independent probability
Unbiased Recommender Systems with Implicit Feedback
Recommender systems typically rely on implicit feedback (e.g., clicks) to infer user preferences. However, such data is inherently prone to various biases, including position bias and popularity bias.
Learning to Price with Persuasion
Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mech
Tight Inapproximability of Pacing and Throttling Equilibria in Second-Price Auctions
Budget-constrained advertisers commonly rely on two control mechanisms: pacing scales bids, whereas throttling randomizes participation. We prove that, in second-price auctions, these two different me
The ultimate carbon cost of a ChatGPT query
This paper reviews and combines findings from the fields of product and life-cycle analysis [36, 38], the usage of modern transformer- based large language models (LLM) [6], as well as on greenhouse g
Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate
Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the
Characterizing Agentic Flooding of Government Services
AI agents are making it easier for the public to interact with government, such as by helping them apply for benefits, understand complex policies, and make their opinions heard. Although improving se
Declining Modularity of Intellectual Bases During the Emergence of Research Areas
Understanding how research areas emerge can help identify nascent areas early and inform research strategy, yet how the intellectual base of a field restructures as an area takes shape remains unclear
"If It Looks Like a User": Measuring Real-Time Moderation Effects via Social Media Simulation
Agent-based social media simulators offer a controlled environment to study content moderation, yet their value hinges on how faithfully they reproduce real platform dynamics. We develop a calibrated
Rigorous Statements and Proofs of the Lemmas in Simon's Algorithm for the Dihedral Coset Problem and Their Underlying Hypothesis
In a recent preprint, Simon proposed a polynomial-time quantum algorithm for the Dihedral Coset Problem and rested the analysis on four lemmas. Three of them carry only proof sketches, and this paper
SAHC-NS: Structure-Aware and Hardness-Calibrated Negative Sampling for Implicit Collaborative Filtering
Negative sampling is a key component of implicit collaborative filtering (CF), as it enables recommenders to effectively learn user preferences. Existing negative sampling methods mostly follow a two-
When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning b
The User Side of AI Model Lifecycles: Evidence from the Keep4o Movement
AI model lifecycles are commonly understood as a series of technical and organizational processes. Yet once a model enters sustained use, subsequent changes can also affect established user practices
Absence of critical scaling in the Schelling segregation model
We find no evidence of critical scaling in the Schelling segregation model, in either the Moore neighborhood or its dense-spectrum extension to Chebyshev radii up to $r_0 = 6$ ($k = 168$ neighbors). O
What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents
Long-term memory enables personalized conversational agents to retain user information across sessions. However, existing memory architectures primarily optimize for utility while neglecting the risks
Anchoring for Truthfulness: The Random-Anchor Volume Mechanism for Multi-Facility Location
We study the strategyproof placement of \(k\) facilities on the real line for \(n\) agents who privately report their locations, without monetary transfers. For two facilities, the Proportional Mechan
DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector
Operationalizing the EU AI Act in Agile Software Development: A Guideline-Based Approach
Context: The EU AI Act requires providers and deployers of Artificial Intelligence (AI) systems to implement documentation, risk management, and human oversight. Agile teams that ship AI features in s
LLMs for Zero-Shot Threat Detection via Structured Risk Indicators
We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from heterogeneous security logs. The framework models use
Vantage: Availability-Graded Broadcast for Signature-Free BFT
Digital signatures make blocks and votes transferable evidence: one party can prove to another what a third party said. Authenticated channels convince only the direct receiver, so existing high-throu
When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval
Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurable class of tool-backed executable skills that m
Solving Streett and Emerson-Lei Games with Universal Trees
Nearly a decade ago, Calude et al. showed that parity games can be solved in quasi-polynomial time. This result is now understood in terms of universal trees. By reduction to parity games, the quasi-p
Fed Proposes AML Program Reforms: Risk-Based Resource Allocation and Effectiveness Supervision
On July 7, 2026, the Federal Reserve Board proposed amendments to AML program requirements for state member banks, bank holding companies, and foreign banking organizations. The rule would allow banks to allocate resources based on risk, mandates board approval, requires a US-based compliance officer, and explicitly encourages adoption of innovative technologies including AI/ML. Simultaneously, FinCEN's April 2026 proposed rule and the GENIUS Act CIP rule for stablecoin issuers create the most significant BSA overhaul in 20+ years.
Levi & Reuter (2006) - Money Laundering: A Review of the Economics of Crime
Levi and Reuter critically review the evidence for AML effectiveness, questioning whether the massive global investment in AML compliance reduces crime. Foundational critique of AML regime effectiveness.
Takats (2007) - A Theory of 'Crying Wolf': The Economics of Money Laundering Enforcement
Takats models how asymmetric incentives lead compliance officers to over-report suspicious activity, creating massive false positive volumes that overwhelm the AML system and reduce its effectiveness.
Unger et al (2007) - The Amounts and Effects of Money Laundering
Unger et al quantify global money laundering at 2-5% of GDP and analyze its macroeconomic effects on growth, interest rates, exchange rates, and income distribution.
Drezner (2022) - The Global Governance of Anti-Money Laundering
Drezner analyzes the FATF-led AML regime as an 'institutional shell' — highly developed formal structure with limited practical effectiveness, serving multiple stakeholders beyond crime reduction.
Soudijn (2021) - Trade-Based Money Laundering
Soudijn examines trade-based money laundering as one of the most difficult-to-detect channels, exploiting trade complexity through over/under-invoicing and phantom shipments to move value across borders.
Naheem (2015) - AML Transaction Monitoring Systems: A Critical Analysis
Naheem critically examines practical challenges in AML transaction monitoring, analyzing rule-based systems' high false positive rates, data quality issues, and the potential of machine learning approaches.
Collier (2020) - The Role of Suspicious Activity Reports in AML
Collier empirically analyzes the UK SARs database, documenting the massive growth in SAR filings, low conversion rates to law enforcement action, and the 'defensive filing' phenomenon.
Bueche (2022) - FATF and Virtual Assets: The Evolution of Global AML Standards for Crypto
Bueche tracks the FATF's extension of AML regulation to virtual assets, including the Travel Rule for crypto transfers, and analyzes implementation challenges in the decentralized finance landscape.
Quantum Spectral Anomaly Detection
A core task in quantum anomaly detection is to compute an anomaly score that quantifies how strongly a test quantum state deviates from a given quantum dataset assumed to be normal. Classically, princ
Square-Root Price Impact Is Necessary for Endogenous Manipulation Cycles in Learning-Agent Markets
We study a minimal agent-based market in which a single evolutionary-optimized institutional agent interacts with 20{,}000 herding retail traders. The agent spontaneously discovers a multi-cycle preda
Streaming ETL for Suspicious Activity Reports: Real-Time AML Data Pipelines with Kafka and Flink
Architecture patterns for building real-time AML surveillance data pipelines using Apache Kafka for transaction ingestion, Flink for stream processing, and Iceberg for immutable audit storage — with DataOps quality gates at every stage.
Data Pipeline Observability in Financial Crime Compliance: Real-Time AML Monitoring at Scale
How DataOps practices including pipeline observability, data quality monitoring, and automated lineage tracking are transforming anti-money laundering transaction monitoring systems at major financial institutions.
Cryptocurrency mixers under global regulatory spotlight after latest sanctions
Analysis of the global regulatory response to cryptocurrency mixing services following OFAC sanctions, including technical analysis of mixer protocols and legal frameworks for enforcement.
AI-powered transaction monitoring: 80% false positive reduction at major European banks
Case study of how five major European banks deployed machine learning for AML transaction monitoring, achieving 80% false positive reduction while improving suspicious activity detection rates.
DeFi platforms face unprecedented AML enforcement actions globally
Global regulators escalate enforcement against decentralized finance platforms for AML violations, with of recent actions by SEC, FCA, and MAS against major DeFi protocols.
FinCEN beneficial ownership reporting: one year of data reveals patterns
Review of the first year of FinCEN's beneficial ownership reporting requirements, analyzing filing patterns, compliance rates, and enforcement actions taken against non-compliant entities.
EU 7th AML Directive implementation challenges across member states
Analysis of the EU's 7th Anti-Money Laundering Directive taking effect in 2026, examining implementation challenges across member states including beneficial ownership registries, cross-border cooperation, and cryptocurrency regulation.
Suspicious Activity Reports: What Every Compliance Professional Should Know
SARs are the primary mechanism for reporting suspicious financial activity. This guide covers when to file, what to include, confidentiality requirements, and common pitfalls for new compliance officers.
Sanctions Screening: How It Works and Why It Matters
Sanctions screening checks customer names against government watchlists. Learn about OFAC, EU sanctions regimes, fuzzy matching algorithms, and false positive reduction strategies.
The Risk-Based Approach in AML: A Practical Introduction
The risk-based approach (RBA) is the core methodology of modern AML compliance. This article explains how institutions assess customer risk, segment their portfolios, and allocate resources proportionally.
Understanding the AML Regulatory Landscape
A beginner-friendly overview of the global AML regulatory framework: FATF recommendations, the Bank Secrecy Act, the EU Anti-Money Laundering Directives, and how they fit together.
KYC Fundamentals: Identity Verification in Financial Services
Know Your Customer (KYC) is the cornerstone of AML compliance. Learn how financial institutions verify identities, assess risk, and screen against watchlists.
What Is Money Laundering? A Beginner's Guide
Money laundering is the process of making illegally obtained money appear legitimate. This guide explains the three stages — placement, layering, integration — with real-world examples.