Optimal Intervention for Self-triggering Spatial Networks with Application to Urban Crime Analytics

2025-05-26

AI Summary

This paper addresses the suppression of cascading adverse events in self-exciting spatiotemporal networks—such as the diffusion of crime hotspots—where traditional purely temporal Hawkes process models fail to capture spatial dependencies. Method: We propose the first optimal node intervention model for spatiotemporal Hawkes networks, jointly modeling geographic proximity and temporal event dependence. Our approach integrates spatiotemporal Hawkes processes, stochastic optimization, and intensity function sensitivity analysis, validated on real-world crime data from Los Angeles. Contribution/Results: By extending intervention optimization from the temporal to the spatiotemporal domain, our method enables precise identification of high-impact intervention regions. Experiments demonstrate substantial superiority over heuristic baselines in simulation; when applied to Los Angeles data, it accurately identifies seven critical communities and achieves an average 31.2% reduction in subsequent crime intensity—delivering interpretable, deployable decision support for predictive policing.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In many network systems, events at one node trigger further activity at other nodes, e.g., social media users reacting to each other's posts or the clustering of criminal activity in urban environments. These systems are typically referred to as self-exciting networks. In such systems, targeted intervention at critical nodes can be an effective strategy for mitigating undesirable consequences such as further propagation of criminal activity or the spreading of misinformation on social media. In our work, we develop an optimal network intervention model to explore how targeted interventions at critical nodes can mitigate cascading effects throughout a Spatiotemporal Hawkes network. Similar models have been studied previously in the literature in purely temporal Hawkes networks, but in our work, we extend them to a spatiotemporal setup and demonstrate the efficacy of our methods by comparing the post-intervention reduction in intensity to other heuristic strategies in simulated networks. Subsequently, we use our method on crime data from the LA police department database to find neighborhoods for strategic intervention to demonstrate an application in predictive policing.

Problem

• Develop optimal intervention for self-triggering spatiotemporal networks
• Mitigate cascading effects like crime propagation using targeted strategies
• Apply model to urban crime data for predictive policing solutions

Innovation

• Optimal intervention model for Spatiotemporal Hawkes networks
• Extends temporal models to spatiotemporal setups
• Applies method to urban crime data analysis