Modelling underreported spatio-temporal crime events

Crime observations are one of the principal inputs used by governments for designing citizens' security strategies. However, crime measurements are obscured by underreporting biases, resulting in the so-called dark figure of crime. This work studies the possibility of recovering true crime and underreported incident rates over time using sequentially available daily data. For this, a novel underreporting model of spatiotemporal events based on the combinatorial multi-armed bandit framework was proposed. Through extensive simulations, the proposed methodology was validated for identifying the fundamental parameters of the proposed model: the true rates of incidence and underreporting of events. Once the proposed model was validated, crime data from a large city, Bogota (Colombia), was used to estimate the true crime and underreporting rates. Our results suggest that this methodology could be used to rapidly estimate the underreporting rates of spatiotemporal events, which is a critical problem in public policy design.

Automated summary

Crime observations are crucial for designing citizens' security strategies, but the dark figure of crime caused by underreporting biases hinders accurate measurements. This study proposes a novel underreporting model based on spatiotemporal events and validates its effectiveness through simulations. The results suggest that this methodology can be used to estimate the underreporting rates of spatiotemporal events, which is essential for public policy design.