Detecting Money Laundering: Exploratory Anomaly Detection of Money Laundering Typologies from FINTRAC Disclosures
Bibliographic record
Abstract
This study presents the findings of a Crime Reduction Research Program (CRRP) project that examines the utility of lightweight, typology-informed analytical techniques for anti-money laundering (AML) detection in resource-limited law enforcement settings. The project, initially aimed at developing an integrated middleware system to analyze structured and unstructured financial intelligence, was re-scoped due to organizational restructuring following the Cullen Commission and pandemic-related capacity shifts. The revised study is a standalone exploratory analysis of FINTRAC Suspicious Transaction Reports and related disclosure data for Project ATHENA (2016–2019), conducted in partnership with the Combined Forces Special Enforcement Unit – British Columbia, the Royal Canadian Mounted Police, and the Ministry of Public Safety and Solicitor General.Drawing on Benford’s Law, feature-engineered indicators, and visual–analytic triage methods, the study evaluates whether accessible, explainable anomaly-detection techniques can improve the early-stage prioritization of pre-flagged financial intelligence. The analysis shows that deviations from expected digit distributions, venue-based clustering, round-dollar transaction patterns, and the innovative measure of casino versatility offer relevant behavioural signals aligned with established laundering typologies, especially those linked to the Vancouver Model. These techniques revealed non-obvious transactional patterns, supported effective data reduction, and allowed for more intuitive interpretation by frontline analysts without dependence on complex enterprise systems.The findings expose critical, persistent structural gaps in Canada’s AML intelligence cycle, particularly in analytical capacity, data accessibility, and inter-agency coordination. This study demonstrates the transformative potential of modular, scalable screening tools designed for practitioners. More broadly, it strengthens the evidence base for innovative socio-technical strategies in the fight against illicit finance, proving that lean, theory-driven computational methods can drive breakthroughs in financial integrity investigations, even amid institutional instability and evolving enforcement priorities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".