Artificial Intelligence and Crime in Latin America: A Multilingual Bibliometric Review (2010–2025)

Artificial intelligence is increasingly used to support public safety by predicting events, uncovering patterns, and informing decisions. In Latin America, where crime burdens are high and data systems are heterogeneous, a region-focused synthesis is needed to assess progress, identify gaps, and clarify operational implications. Accordingly, this PRISMA-guided, multilingual (English, Spanish, and Portuguese) bibliometric review synthesizes 146 peer-reviewed journal articles (2010–October 2025) to examine trends, methods, and application domains. Since 2018, publication output accelerated, peaking in 2024–2025. Regionally, Brazil leads within a multi-hub co-authorship network linking Latin American nodes to the United States and Spain; additional hubs include Colombia, Chile, Mexico, Ecuador, and Peru. Methodologically, three motifs dominate: temporal-dependence modeling; ensemble learners with cost-sensitive decision rules; and multimodal integration of remote sensing and computer vision with administrative data. At the application level, four families prevail: utility and fiscal-fraud analytics; environmental offenses with temporal modeling; cyber and platform-based analytics; and sensing, geospatial, and forensic workflows. However, evaluation practices are heterogeneous, with frequent risks of spatial or temporal leakage; moreover, reporting on fairness, accountability, and transparency is limited. In order to support responsible scaling, research directions include interoperable data governance, leakage-controlled and cost-sensitive evaluation, domain adaptation that accounts for spatial dependence, open and auditable benchmarks, and broader regional participation. To our knowledge, this review is one of the first multilingual, region-centered syntheses of artificial intelligence and crime in Latin America, and it establishes a reproducible baseline and an actionable evidence map that enable comparable, leakage-controlled evaluation and inform research, funding, and public safety policy in the region.