The work presents a comparative study of classical, quantum, transformer-based, and hybrid machine learning approaches for Anti-Money Laundering (AML) detection using the IBM AML transaction dataset. The study evaluates multiple classical and quantum models under a unified experimental framework, proposes a two-stage hybrid pipeline combining Isolation Forest with quantum classifiers, and validates selected quantum models on real IBM Quantum hardware. The paper also incorporates statistical significance analysis and runtime comparisons to assess both predictive performance and practical feasibility. Overall, the work provides a comprehensive benchmark of current classical and near-term quantum approaches for AML detection while exploring the practical applicability of hybrid quantum machine learning under existing NISQ hardware constraints.
(write your relevancy here)
(write your future scope here)
(write your Skills acquired here)
