Application of Gradient Boosting Algorithms for Anti-money Laundering in Cryptocurrencies

Abstract

The recent emergence of cryptocurrencies has added another layer of complexity in the fight towards financial crime. Cryptocurrencies require no central authority and offer pseudo-anonymity to its users, allowing criminals to disguise themselves among legitimate users. On the other hand, the openness of data fuels the investigator's toolkit to conduct forensic examinations. This study focuses on the detection of illicit activities (e.g., scams, financing terrorism, and Ponzi schemes) on cryptocurrency infrastructures, both at an account and transaction level. Previous work has identified that class imbalance and the dynamic environment created by the evolving techniques deployed by criminals to avoid detection are widespread in this domain. In our study, we propose Adaptive Stacked eXtreme Gradient Boosting (ASXGB), an adaptation of eXtreme Gradient Boosting (XGBoost), to better handle dynamic environments and present a comparative analysis of various offline decision tree-based ensembles and heuristic-based data-sampling techniques. Our results show that: (i) offline decision treebased gradient boosting algorithms outperform state-of-the-art Random Forest (RF) results at both an account and transaction level, (ii) the data-sampling approach NCL-SMOTE further improves recall at a transaction level, and (iii) our proposed ASXGB successfully reduced the impact of concept drift while further improving recall at a transaction level.

Feature Engineering and Resampling Strategies for Fund Transfer Fraud With Limited Transaction Data and a Time-Inhomogeneous Modi Operandi

“…We find that modus operandi patterns can be divided into several subgroups as observed from a scatter plot projected from high-dimensional feature vectors of accounts. Thus, even through Vassallo et al [27] suggest that SMOTE-NCL is especially useful for dealing with financial data imbalance, our experiments show that SMOTE-related approaches yield degraded prediction for time-inhomogeneous fraud detection. This is because interpolations adopted by SMOTE-related methods can improperly place synthesized positive observations where negative observations are dense and/or change the statistical properties of features belonging to positive observations.…”

“…Ghorbani and Ghousi [34] and Hordri et al [35] compare different resampling methods, including SMOTE, borderline SMOTE, SMOTE-ENN, SVM-SMOTE, SMOTE-Tomek, and random under/oversampling. Vassallo et al [27] claim that SMOTE-NCL is especially useful for dealing with financial data imbalance. We compare the above methods in our experiments, and consider the Wasserstein GANs [24].…”

“…In addition to predicting modi operandi, the ability to interpret the predictions for summing up the patterns of modi operandi is also essential for an FTF detection system to pinpoint the vulnerabilities of the procedures of financial services. Indeed, profiling modi operandi prevents fraudsters from utilizing fund transfer systems (see [25]) and fulfilling the "risk-oriented" 4 property asked for by the Financial Action Task Force 5 (see [26] and [27]). Our proposed behavioral and segmentation features provide a clear causeeffect relationship between features and fraudulent labels.…”

A Time-Frequency Based Suspicious Activity Detection for Anti-Money Laundering

“…Node2vec and random walk can be used to create new feature vectors for nodes, improving the model detection performance [38]. In an another recent study, different type of gradient boosting and random forest algorithms have been applied for the detection of anti-money laundering in cryptocurrency networks [39].…”

Significant of Gradient Boosting Algorithm in Data Management System

“…And with the help of the two techniques, Gradient-based-side sampling and the exclusive feature bundling, the LightGBM can significantly perform better than the other known models in terms of computational speed and memory consumption which is a basic essence for gradient boosting. Vassallo et al (2021) on the application of gradient boosting algorithms for anti-money laundering in crypto-currencies, investigated the potential application of the decision treebased gradient boosting algorithm in conjunction with efficient hyper-parameter optimization and data sampling techniques. Fighting financial crimes has been very much around for as long as one can imagine, but the introduction of crypto-currencies just added another layer of complexity in the fight against financial crimes.…”