Applying machine learning to criminology: semi-parametric spatial-demographic Bayesian regression

Marchant, Román; Haan, S.; Clancey, Garner; Cripps, Sally

doi:10.1186/s13388-018-0030-x

Cited by 16 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present study aims to build a predictive modelling framework for rape reporting delays. Over the last years, machine learning methods have become increasingly popular in crime research [23][24][25], particularly focusing on the spatial, temporal or spatio-temporal dimensions. For instance, recent studies have approached issues such as forecasting domestic violence [26], spatio-temporal contagion of gun violence [27] and prediction of criminal activity [28].…”

mentioning

confidence: 99%

Understanding spatial patterns in rape reporting delays

2021

View full text Add to dashboard Cite

Under-reporting and delayed reporting of rape crime are severe issues that can complicate the prosecution of perpetrators and prevent rape survivors from receiving needed support. Building on a massive database of publicly available criminal reports from two US cities, we develop a machine learning framework to predict delayed reporting of rape to help tackle this issue. Motivated by large and unexplained spatial variation in reporting delays, we build predictive models to analyse spatial, temporal and socio-economic factors that might explain this variation. Our findings suggest that we can explain a substantial proportion of the variation in rape reporting delays using only openly available data. The insights from this study can be used to motivate targeted, data-driven policies to assist vulnerable communities. For example, we find that younger rape survivors and crimes committed during holiday seasons exhibit longer delays. Our insights can thus help organizations focused on supporting survivors of sexual violence to provide their services at the right place and time. Due to the non-confidential nature of the data used in our models, even community organizations lacking access to sensitive police data can use these findings to optimize their operations.

show abstract

mentioning

confidence: 99%

Understanding spatial patterns in rape reporting delays

2021

View full text Add to dashboard Cite

show abstract

“…The generalized, additive geo-spatial regression models used had specific components to measure aspects related to geographic information systems (GIS), which are widely used in credibility models in various areas, such as finance (Bozkurt et al, 2018), crime (Marchant et al, 2018), traffic (Do et al, 2019, climate (Lima et al, 2016) and epidemiology (Martinez et al, 2020). Its advantage lies in the possibility to allow addition of geo-demographic variables and concepts of spatial smoothing.…”

Section: Discussionmentioning

confidence: 99%

Homicides of black people in Brazil: A study of different regions, using generalized additive regression models-with a geo-spatial component

Lizzi¹,

Garrido²,

Xavier³

et al. 2021

Geospat Health

View full text Add to dashboard Cite

The number of homicides in Brazil has reached record numbers, and when the race/colour of the victims is considered-an extreme inequality is evident- with a particularly high number of deaths in black and brown populations. The goal of this work was to analyse homicide rates of black people in Brazil from the years 2000 to 2016, using generalized additive regression models, with a geo-spatial component. The statistics were applied to understand the social reasons for homicide risks in the black population in Brazil’s 26 states and Federal District with reference to the human development index and its components (education, longevity and income) as well as social inequality indices (Gini and Theil). This socioecological, epidemiological study to estimate the risk of homicide in the black population with a time series component, shows that this risk has increased linearly over time. Less longevity and low income correlated with a greater risk of homicide-while the Gini and Theil indices showed that in places where there are greater inequalities, there is also a higher risk of homicide in both black and non-black populations. The results - regarding the possibility of relating social indicators to homicide risk in the regional units under study, would support implementation of interventional public policy measures.

show abstract

“…A probabilistic model based on the Bayesian paradigm was suggested by [78]. This proposed model was conceived to predict spatial crime rates using demographic and historical crime data.…”

Section: Related Work: ML and Crime Predictionmentioning

confidence: 99%

Predicting Spatial Crime Occurrences through an Efficient Ensemble-Learning Model

Lamari

Freškura²,

Abdessamad

et al. 2020

IJGI

View full text Add to dashboard Cite

While the use of crime data has been widely advocated in the literature, its availability is often limited to large urban cities and isolated databases that tend not to allow for spatial comparisons. This paper presents an efficient machine learning framework capable of predicting spatial crime occurrences, without using past crime as a predictor, and at a relatively high resolution: the U.S. Census Block Group level. The proposed framework is based on an in-depth multidisciplinary literature review allowing the selection of 188 best-fit crime predictors from socio-economic, demographic, spatial, and environmental data. Such data are published periodically for the entire United States. The selection of the appropriate predictive model was made through a comparative study of different machine learning families of algorithms, including generalized linear models, deep learning, and ensemble learning. The gradient boosting model was found to yield the most accurate predictions for violent crimes, property crimes, motor vehicle thefts, vandalism, and the total count of crimes. Extensive experiments on real-world datasets of crimes reported in 11 U.S. cities demonstrated that the proposed framework achieves an accuracy of 73% and 77% when predicting property crimes and violent crimes, respectively.

show abstract

Applying machine learning to criminology: semi-parametric spatial-demographic Bayesian regression

Cited by 16 publications

References 27 publications

Understanding spatial patterns in rape reporting delays

Understanding spatial patterns in rape reporting delays

Homicides of black people in Brazil: A study of different regions, using generalized additive regression models-with a geo-spatial component

Predicting Spatial Crime Occurrences through an Efficient Ensemble-Learning Model

Contact Info

Product

Resources

About