A Systematic Review of Artificial Intelligence Applied to Compliance: Fraud Detection in Cryptocurrency Transactions
Bibliographic record
Abstract
Rising financial fraud impacts industries, economies, and consumers, creating a need for advanced technological solutions. Compliance frameworks help detect and prevent illicit activities like money laundering, market manipulation, etc. However, with the rise of cryptocurrencies and blockchain, traditional detection methods are ineffective. As a result, Artificial Intelligence (AI) has emerged as a vital tool for combating fraud in the cryptocurrency sector. This systematic review examines the integration of AI in compliance for cryptocurrency fraud detection between 2014 and 2025, analyzing its evolution, methodologies, and emerging trends. Using RStudio (Biblioshiny) and VOSviewer, 353 peer-reviewed studies from leading databases including SciSpace, Elicit, Google Scholar, ScienceDirect, Scopus, and Web of Science were analyzed following the PRISMA methodology. Key trends include the adoption of machine learning, deep learning, natural language processing, and generative AI technologies to improve efficiency and innovation in fraud detection. However, challenges persist, including limited transparency in AI models, regulatory fragmentation, and limited access to quality data, all of which hinder effective fraud detection. The long-term real-world effectiveness of AI tools remains underexplored. This review highlights the trajectory of AI in compliance, identifies areas for further research, and emphasizes bridging theory and practice to strengthen fraud detection in cryptocurrency transactions.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.084 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.006 |
| Bibliometrics | 0.024 | 0.025 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".