TY - GEN
T1 - Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity
AU - Lorenz, Joana
AU - Silva, Maria Inês
AU - Aparício, David
AU - Ascensão, João Tiago
AU - Bizarro, Pedro
N1 - Lorenz, J., Silva, M. I., Aparício, D., Ascensão, J. T., & Bizarro, P. (2020). Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity. In ICAIF 2020 - 1st ACM International Conference on AI in Finance (pp. 1-8). [3422549] (ICAIF 2020 - 1st ACM International Conference on AI in Finance). Association for Computing Machinery, Inc. https://doi.org/10.1145/3383455.3422549
PY - 2020/10/15
Y1 - 2020/10/15
N2 - Every year, criminals launder billions of dollars acquired from serious felonies (e.g., terrorism, drug smuggling, or human trafficking), harming countless people and economies. Cryptocurrencies, in particular, have developed as a haven for money laundering activity. Machine Learning can be used to detect these illicit patterns. However, labels are so scarce that traditional supervised algorithms are inapplicable. Here, we address money laundering detection assuming minimal access to labels. First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset. Then, we show that our proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5% of the labels. This solution mimics a typical real-life situation in which a limited number of labels can be acquired through manual annotation by experts.
AB - Every year, criminals launder billions of dollars acquired from serious felonies (e.g., terrorism, drug smuggling, or human trafficking), harming countless people and economies. Cryptocurrencies, in particular, have developed as a haven for money laundering activity. Machine Learning can be used to detect these illicit patterns. However, labels are so scarce that traditional supervised algorithms are inapplicable. Here, we address money laundering detection assuming minimal access to labels. First, we show that existing state-of-the-art solutions using unsupervised anomaly detection methods are inadequate to detect the illicit patterns in a real Bitcoin transaction dataset. Then, we show that our proposed active learning solution is capable of matching the performance of a fully supervised baseline by using just 5% of the labels. This solution mimics a typical real-life situation in which a limited number of labels can be acquired through manual annotation by experts.
KW - Active learning
KW - Anomaly detection
KW - Anti money laundering
KW - Cryptocurrency
KW - Supervised classification
UR - http://www.scopus.com/inward/record.url?scp=85118130840&partnerID=8YFLogxK
U2 - 10.1145/3383455.3422549
DO - 10.1145/3383455.3422549
M3 - Conference contribution
AN - SCOPUS:85118130840
T3 - ICAIF 2020 - 1st ACM International Conference on AI in Finance
SP - 1
EP - 8
BT - ICAIF 2020 - The First ACM International Conference on AI in Finance
PB - ACM - Association for Computing Machinery
T2 - 1st ACM International Conference on AI in Finance, ICAIF 2020
Y2 - 15 October 2020 through 16 October 2020
ER -