A Scalable Digital System for Financial Forensics in Classifying Illicit Addresses on the Bitcoin Networks
Bibliographic record
Abstract
Bitcoin and its blockchain technology allow criminals to conduct illicit transactions while hiding in plain sight. However, anti-money laundering regulations, combined with machine learning techniques, have the capability of identifying and tracking these illicit actors by utilizing Bitcoin’s publicly available information. Establishing whether a Bitcoin address is likely involved with illicit transactions is a tool that would significantly improve regulation and safety in cryptocurrencies. For example, cryptocurrency exchanges could (a) utilize such a tool to gain valuable insights into customers and (b) establish relationships between illicit Bitcoin addresses and an individual’s identity. In this paper, we present a scalable digital system that explores machine learning models to perform a binary classification on Bitcoin addresses, predicting that an address is involved in illegal transactions (illicit), or that an address has not been involved in any illicit transactions (licit). We train several machine learning models—including Logistic Regression, Multilayer Perceptron, Random Forest, Extreme Gradient Boosting (XGB), and Balanced Random Forest—on variations of data attempting to mitigate the severe class imbalance of the data. Evaluation results show that XGB produces the best metrics. Moreover, we present the features with the strongest influence on the model’s decisions and analyze how they differ between illicit and licit Bitcoin addresses.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".