Khem Raj Bhatt, Krishna Sharma
arXiv 4 Mar 2026 · Machine Learning
arXiv:2603.04328 · PDF · DOI · OpenAlex · Extracted main text
We study the deployment performance of machine learning based enforcement systems used in cryptocurrency anti money laundering (AML). Using forward looking and rolling evaluations on Bitcoin transaction data, we show that strong static classification metrics substantially overstate real world regulatory effectiveness. Temporal nonstationarity induces pronounced instability in cost sensitive enforcement thresholds, generating large and persistent excess regulatory losses relative to dynamically optimal benchmarks. The core failure arises from miscalibration of decision rules rather than from declining predictive accuracy per se. These findings underscore the fragility of fixed AML enforcement policies in evolving digital asset markets and motivate loss-based evaluation frameworks for regulatory oversight.
appendix boundary found by appendix_command · 68% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Elkan, Charles (2001) The foundations of cost-sensitive learning | 1.000 | 5 | 4 | 100% |
| 2 | Danielsson, Jon and James, Kevin R and Valenzuela, Marcela and Zer,… (2016) Model risk of risk models | 0.928 | 4 | 4 | 100% |
| 3 | Anagnostopoulos, Ioannis (2018) Fintech and regtech: Impact on regulators and banks | 0.843 | 3 | 3 | 100% |
| 4 | Baek, Chung and Elbeck, Matt (2015) Bitcoins as an investment or speculative vehicle? A first look | 0.843 | 3 | 3 | 100% |
| 5 | Baur, Dirk G and Hong, KiHoon and Lee, Adrian D (2018) Bitcoin: Medium of exchange or speculative assets? | 0.843 | 3 | 3 | 100% |
| 6 | Biais, Bruno and Bisiere, Christophe and Bouvard, Matthieu and Casam… (2023) Equilibrium bitcoin pricing | 0.843 | 3 | 3 | 100% |
| 7 | Gama, João and Zliobaitė, Indrė and Bifet, Albert and Pechenizkiy, M… (2014) A survey on concept drift adaptation | 0.843 | 3 | 3 | 100% |
| 8 | Oztas, Berkan and Cetinkaya, Deniz and Adedoyin, Festus and Budka, M… (2024) Transaction monitoring in anti-money laundering: A qualitative analysis and points of view from industry | 0.843 | 3 | 3 | 100% |
| 9 | Widmer, Gerhard and Kubat, Miroslav (1996) Learning in the presence of concept drift and hidden contexts | 0.843 | 3 | 3 | 100% |
| 10 | Bailey, David and Borwein, Jonathan and Lopez de Prado, Marcos and Z… (2017) The probability of backtest overfitting | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 32 scored citations.