Combating Financial Crimes with Unsupervised Learning Techniques: Clustering and Dimensionality Reduction for Anti-Money Laundering

ArXiv ID: 2403.00777 “View on arXiv”

Authors: Unknown

Abstract

Anti-Money Laundering (AML) is a crucial task in ensuring the integrity of financial systems. One keychallenge in AML is identifying high-risk groups based on their behavior. Unsupervised learning, particularly clustering, is a promising solution for this task. However, the use of hundreds of features todescribe behavior results in a highdimensional dataset that negatively impacts clustering performance.In this paper, we investigate the effectiveness of combining clustering method agglomerative hierarchicalclustering with four dimensionality reduction techniques -Independent Component Analysis (ICA), andKernel Principal Component Analysis (KPCA), Singular Value Decomposition (SVD), Locality Preserving Projections (LPP)- to overcome the issue of high-dimensionality in AML data and improve clusteringresults. This study aims to provide insights into the most effective way of reducing the dimensionality ofAML data and enhance the accuracy of clustering-based AML systems. The experimental results demonstrate that KPCA outperforms other dimension reduction techniques when combined with agglomerativehierarchical clustering. This superiority is observed in the majority of situations, as confirmed by threedistinct validation indices.

Keywords: Anti-Money Laundering (AML), Clustering, Dimensionality Reduction, Kernel PCA, Unsupervised Learning, Cross-Asset / Compliance & Risk

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 4.0/10
• Quadrant: Lab Rats
• Why: The paper employs advanced mathematical techniques like KPCA and ICA but lacks implementation details, code, or specific backtesting results, relying instead on general validation indices.

  flowchart TD
    subgraph Research Goal
        A["Goal: Improve Clustering for AML<br/>(High-Dimensional Challenge)"]
    end

    subgraph Data Input
        B["AML Dataset<br/>(Hundreds of Features)"]
    end

    subgraph Methodology
        C["Apply Dimensionality Reduction Techniques"]
        D["Perform Agglomerative Hierarchical Clustering"]
    end

    subgraph Key Findings
        E["Kernel PCA (KPCA)<br/>Outperforms ICA, SVD, LPP<br/>Validated by 3 Indices"]
    end

    A --> B
    B --> C
    C --> D
    D --> E