Spatio-Temporal-Network Point Processes for Modeling Crime Events with Landmarks

2024-09-17

AI Summary

Existing self-exciting point process models represent crime events in continuous Euclidean space, neglecting street network topology and urban infrastructure constraints. This work proposes a street-network-constrained crime modeling framework: event space is defined directly on the real-world road network topology; spatiotemporal dependencies are measured via network distance; and nearby landmark types serve as multimodal event marks to capture the influence of urban design on crime mixing patterns. For the first time, we jointly integrate street network geometry, landmark semantics, and self-exciting point processes, designing a graph attention network (GAT)-based mark interaction learning module that overcomes Euclidean assumptions and static spatial partitioning. Evaluated on real-world crime data from Valencia, Spain, our model achieves significant improvements in short-term crime risk prediction accuracy and uncovers landmark-driven crime propagation mechanisms and spatially heterogeneous patterns.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Self-exciting point processes are widely used to model the contagious effects of crime events living within continuous geographic space, using their occurrence time and locations. However, in urban environments, most events are naturally constrained within the city's street network structure, and the contagious effects of crime are governed by such a network geography. Meanwhile, the complex distribution of urban infrastructures also plays an important role in shaping crime patterns across space. We introduce a novel spatio-temporal-network point process framework for crime modeling that integrates these urban environmental characteristics by incorporating self-attention graph neural networks. Our framework incorporates the street network structure as the underlying event space, where crime events can occur at random locations on the network edges. To realistically capture criminal movement patterns, distances between events are measured using street network distances. We then propose a new mark for a crime event by concatenating the event's crime category with the type of its nearby landmark, aiming to capture how the urban design influences the mixing structures of various crime types. A graph attention network architecture is adopted to learn the existence of mark-to-mark interactions. Extensive experiments on crime data from Valencia, Spain, demonstrate the effectiveness of our framework in understanding the crime landscape and forecasting crime risks across regions.

Problem

• Modeling crime events constrained by urban street network geography
• Capturing crime patterns influenced by urban infrastructure distribution
• Understanding how urban design affects mixing structures of crime types

Innovation

• Uses street network as underlying event space
• Measures distances via street network paths
• Incorporates landmark types with crime categories