Exploring the Relationship between Road Network and Vehicle Theft in São Paulo

• Grant number: 24/07478-8
• Support Opportunities: Scholarships in Brazil - Master
• Start date: December 01, 2024
• End date: May 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Luis Gustavo Nonato
• Grantee: Raissa Rosa dos Santos Januário
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 22/09091-8 - Criminality, insecurity, and legitimacy: a transdisciplinary approach, AP.ESCIENCE.TEM

Abstract

In recent years, studies in criminology have increasingly considered urban infrastructure as a crucial factor that can influence the occurrence of crimes. However, few have specialized in analyzing the road network as a possible determinant for the incidence of these occurrences in certain locations. In this context, this project aims to present a computational approach to analyze the influence of the road network on vehicle theft in the city of São Paulo - SP, Brazil. The use of computational mathematical algorithms is proposed for calculating hotspots, where spatial discretization is based on a street network, employing kernels defined on graphs (derived from Markov chains) in hotspot calculation. The study of a possible relationship between vehicle theft hotspots and the organization of the road network will be conducted through a combination of graph neural networks and Explainable Artificial Intelligence (XAI) methods.