Dynamic Urban Crime Mapping: Integrating Spatio-Temporal Analysis for Predictive Modeling

• Grant number: 23/16334-7
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: February 01, 2024
• End date: January 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Antonio Castelo Filho
• Grantee: Waqar Hassan
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID

Abstract

Urbanization presents a dual challenge of opportunities and crime, with the latter standing out prominently among the issues urban centers face globally. Addressing crime beyond reacting to incidents requires anticipating, mitigating, and preventing through informed decision-making. This research recognizes the complexity of the criminal network and its rules, emphasizing the need to understand crime dynamics influenced by socioeconomic conditions, demographics, environment, and historical trends. Crime analysis traditionally relies on spatial and temporal techniques, but this project asserts the inadequacy of conventional static mapping in capturing temporal dynamics. Integrating machine learning (ML) models and spatiotemporal analysis is proposed to enhance predictive crime modeling. The project aims to bridge the gap between data science, predictive analytics, and urban planning to create robust tools for public security policies. The research adopts a multidisciplinary approach, necessitating collaboration with Social Sciences and Humanities researchers. It includes developing a comprehensive spatio-temporal crime mapping framework, analyzing historical crime data, implementing machine learning algorithms, and evaluating the model's effectiveness compared to traditional static mapping. The results will be disseminated through scientific journals and mainstream media articles, contributing to the intersection of data science, urban planning, and crime analysis.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

HASSAN, WAQAR; CABRAL, MARVIN MENDES; RAMOS, THIAGO RODRIGO; FILHO, ANTONIO CASTELO; NONATO, LUIS GUSTAVO. Modeling and Predicting Crimes in the City of Sao Paulo Using Graph Neural Networks. INTELLIGENT SYSTEMS, BRACIS 2024, PT III, v. 15414, p. 15-pg., 2025-01-01. (23/15618-1, 22/09091-8, 13/07375-0, 23/16334-7)