Mobility, Nonstationary Density, and Robbery Distribution in the Tourist Metropolis.

This study looks at the spatial distribution of robbery against residents as a function of nonstationary density and mobility patterns in the most densely populated city in Spain, Barcelona. Based on the geographical coordinates of mobile devices, we computed two measures of density of the ambient population and the tourist presence, for work days, weekends, and holidays in 2019. Negative binomial regressions are then estimated to analyse whether these measures are correlated with the risk of robbery, controlling for land use and the characteristics of the social environment. The model reveals that residents' chances of being exposed to robbery in Barcelona depend on the social relevance and tourism attractiveness of certain places at particular times of the year. Our results disclose two sources of social disorganization as stronger predictors of the occurrence of robbery in Barcelona, respectively linked to structural processes of residential instability and daily and seasonal mobility patterns. On the one hand, we found that the effect of the density of international tourists on the outcome variable is mediated by residential volatility, which is assumed to be associated with housing shortages in neighbourhoods where short-term vacation rentals are widespread. On the other hand, the ability to exert effective social control is significantly undermined in urban areas, where the ambient population and the volume of tourists outnumber the resident population, thus increasing incidents of robbery victimization. The implications of these findings for urban policy and crime prevention in the Catalan capital are discussed.

Predicting Domestic Abuse (Fairly) and Police Risk Assessment

Domestic abuse victim risk assessment is crucial for providing victims with the correct level of support. However, it has been shown that the approach currently taken by most UK police forces, the Domestic Abuse, Stalking, and Honour Based Violence (DASH) risk assessment, is not identifying the most vulnerable victims. Instead, we tested several machine learning algorithms and propose a predictive model, using logistic regression with elastic net as the best performing, that incorporates information readily available in police databases, and census-area-level statistics. We used data from a large UK police force including 350,000 domestic abuse incidents. Our models made significant improvement upon the predictive capacity of DASH, both for intimate partner violence (IPV; AUC = .748) and other forms of domestic abuse (non-IPV; AUC = .763). The most influential variables in the model were of the categories criminal history and domestic abuse history, particularly time since the last incident. We show that the DASH questions contributed almost nothing to the predictive performance. We also provide an overview of model fairness performance for ethnic and socioeconomic subgroups of the data sample. Although there were disparities between ethnic and demographic subgroups, everyone benefited from the increased accuracy of model-based predictions when compared with officer risk predictions. (AU)

La evaluación de riesgo de las víctimas de abuso doméstico es crucial para poder ofrecerle a las mismas el nivel adecuado de asistencia. No obstante, se ha demostrado que el enfoque predominante en casi todas las fuerzas policiales británicas, que descansa en el uso de DASH (las iniciales en inglés del instrumento de evaluación de abuso doméstico, acoso y violencia por cuestión de honor), no sirve para identificar a las víctimas más vulnerables. En su lugar, este artículo evalúa varios algoritmos de aprendizaje automático y propone un modelo predictivo, usando como algoritmo con un mejor rendimiento una regresión logística con red elástica, que utiliza como fuente de información variables normalmente disponibles en los archivos policiales, así como en el censo de la población. Para desarrollar y evaluar este modelo usamos datos de un departamento policial responsable de un área metropolitana en el Reino Unido que incluía 350,000 incidentes de abuso doméstico. Nuestros modelos mejoran significativamente la capacidad predictiva de DASH, tanto para la violencia en la relación de pareja (AUC = .748) como para otras formas de abuso doméstico (AUC = .763). Las variables más influyentes en el modelo fueron medidas del historial delictivo y de violencia doméstica previa, en particular el tiempo transcurrido desde el último incidente. El artículo demuestra que el cuestionario DASH prácticamente no contribuye nada al rendimiento predictivo de nuestro modelo. El artículo también ofrece una evaluación del rendimiento en términos de equidad para distintos grupos étnicos y socioeconómicos en nuestra muestra. Aunque había disparidad entre estos subgrupos, todos ellos se beneficiaban de la mayor precisión predictiva resultante de usar nuestros modelos en lugar de las clasificaciones policiales basadas en DASH. (AU)

Predicting Domestic Abuse (Fairly) and Police Risk Assessment.

Domestic abuse victim risk assessment is crucial for providing victims with the correct level of support. However, it has been shown that the approach currently taken by most UK police forces, the Domestic Abuse, Stalking, and Honour Based Violence (DASH) risk assessment, is not identifying the most vulnerable victims. Instead, we tested several machine learning algorithms and propose a predictive model, using logistic regression with elastic net as the best performing, that incorporates information readily available in police databases, and census-area-level statistics. We used data from a large UK police force including 350,000 domestic abuse incidents. Our models made significant improvement upon the predictive capacity of DASH, both for intimate partner violence (IPV; AUC = .748) and other forms of domestic abuse (non-IPV; AUC = .763). The most influential variables in the model were of the categories criminal history and domestic abuse history, particularly time since the last incident. We show that the DASH questions contributed almost nothing to the predictive performance. We also provide an overview of model fairness performance for ethnic and socioeconomic subgroups of the data sample. Although there were disparities between ethnic and demographic subgroups, everyone benefited from the increased accuracy of model-based predictions when compared with officer risk predictions.

La evaluación de riesgo de las víctimas de abuso doméstico es crucial para poder ofrecerle a las mismas el nivel adecuado de asistencia. No obstante, se ha demostrado que el enfoque predominante en casi todas las fuerzas policiales británicas, que descansa en el uso de DASH (las iniciales en inglés del instrumento de evaluación de abuso doméstico, acoso y violencia por cuestión de honor), no sirve para identificar a las víctimas más vulnerables. En su lugar, este artículo evalúa varios algoritmos de aprendizaje automático y propone un modelo predictivo, usando como algoritmo con un mejor rendimiento una regresión logística con red elástica, que utiliza como fuente de información variables normalmente disponibles en los archivos policiales, así como en el censo de la población. Para desarrollar y evaluar este modelo usamos datos de un departamento policial responsable de un área metropolitana en el Reino Unido que incluía 350,000 incidentes de abuso doméstico. Nuestros modelos mejoran significativamente la capacidad predictiva de DASH, tanto para la violencia en la relación de pareja (AUC = .748) como para otras formas de abuso doméstico (AUC = .763). Las variables más influyentes en el modelo fueron medidas del historial delictivo y de violencia doméstica previa, en particular el tiempo transcurrido desde el último incidente. El artículo demuestra que el cuestionario DASH prácticamente no contribuye nada al rendimiento predictivo de nuestro modelo. El artículo también ofrece una evaluación del rendimiento en términos de equidad para distintos grupos étnicos y socioeconómicos en nuestra muestra. Aunque había disparidad entre estos subgrupos, todos ellos se beneficiaban de la mayor precisión predictiva resultante de usar nuestros modelos en lugar de las clasificaciones policiales basadas en DASH.

Lethal and nonlethal violence against an intimate female partner: comparing male murderers to nonlethal abusers.

Men's lethal and nonlethal violence against an intimate female partner are compared. Various risk factors are examined to compare men's lethal and nonlethal violence against an intimate woman partner. Relative to abusers, men who kill are generally more conventional with respect to childhood backgrounds, education, employment, and criminal careers, are more likely to be possessive and jealous, and are more likely to be separated from their partner at the time of the event. Men who kill are more likely to have used violence against a previous partner, to have sexually assaulted and strangled the victim, and to have used a weapon or instrument. However, they were less likely to have been drunk at the time of the event and/or to have previously used violence against the woman they killed. Overall, the findings do not support the notion of a simple progression from nonlethal to lethal violence and raise some dilemmas for the growing area of risk assessment.