This paper examines the evolution of data-driven compliance and fraud detection within the U.S. financial sector from 2010 to 2025, integrating multi-source regulatory and institutional datasets. Using descriptive, geospatial, and correlational analyses, data were drawn from the Financial Crimes Enforcement Network (FinCEN) Suspicious Activity Reports (SARs), Federal Deposit Insurance Corporation (FDIC) Bank Data API, Consumer Financial Protection Bureau (CFPB) complaint records, and the Federal Reserve’s Financial Accounts (Z.1). The findings reveal a progressive shift from traditional rule-based oversight toward algorithmic, technology-enabled supervision emphasizing automation, interoperability, and accountability. Fraud-related SARs increased sharply between 2020 and 2024, coinciding with pandemic-era digital expansion and speculative financial activity. Correlation analysis identified significant relationships between household debt-to-income ratios and fraud-related SARs (r = .65, p < .05), and between equity market capitalization and investment scam typologies (r = .52, p < .05), linking macro-financial cycles with compliance pressures. Simultaneously, artificial intelligence (AI) and machine learning (ML) adoption in compliance functions among major U.S. banks rose from 18% in 2015 to 75% in 2024, reflecting systemic digital transformation. However, disparities persist between large and small institutions in governance and implementation capacity. The results underscore the need for explainable AI (XAI) frameworks, inter-agency data fusion, and integration of macro-prudential indicators into compliance analytics to strengthen fraud resilience. Overall, the study contributes to understanding how digital technologies and financial cycles jointly shape the emerging architecture of regulatory intelligence and consumer protection.