Chaotic Dynamics in Bitcoin Money Laundering: A Recurrence Quantification Analysis

Money laundering in cryptocurrency networks poses persistent challenges for financial intelligence units due to the pseudo-anonymous architecture of blockchain systems and the limited effectiveness of conventional rule-based detection methods. This study introduces chaos theory and recurrence quantification analysis (RQA) as a novel framework for characterizing temporal behavioral dynamics in Bitcoin money laundering transactions. Analyzing 46,564 labeled transactions from the Elliptic Bitcoin Dataset spanning 2009-2018, we construct aggregate time series for illicit and licit transaction volumes across 49 discrete temporal steps, corresponding to the dataset’s inherent graph-based snapshot structure, and apply phase space reconstruction techniques to compute three RQA metrics: determinism (DET), laminarity (LAM), and entropy (ENTR). Results reveal paradoxically higher determinism in illicit transactions (38.24% vs. 16.67% for licit), substantially elevated laminarity (35.80% vs. 0.00%), and greater entropy (0.45 vs. 0.00%), indicating that sophisticated obfuscation strategies inadvertently introduce detectable deterministic signatures. Augmenting conventional graph-based features with RQA metrics significantly enhances Random Forest classification performance, reaching near-optimal levels (F1 = 1.000, AUC = 1.000) within the evaluated dataset environment, with entropy emerging as the single most discriminative predictor. While these exceptional results reflect the high fidelity of chaos-based features in capturing structured laundering patterns from this period, they serve as a benchmark for the theoretical potential of nonlinear analysis in blockchain forensics. These findings demonstrate that temporal complexity features offer a powerful diagnostic tool for real-time monitoring and detection of systemic financial crime in evolving cryptocurrency ecosystems.