Crime Feeds on Legal Activities: Daily Mobility Flows Help to Explain Thieves’ Target Location Choices

Song, Guangwen; Bernasco, Wim; Lin, Liu; Xiao, Luzi; Zhou, Suhong; Liao, Weiwei

doi:10.1007/s10940-019-09406-z

Cited by 58 publications

(44 citation statements)

References 72 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another is to attempt to measure the ambient population of individuals using a particular space, which tends to diverge from residential census estimates (Andresen 2006). Studies have estimated the ambient population via journey-to-work estimates (Boivin and Felson 2018;Stults and Hasbrouck 2015), twitter postings (Hipp et al 2018;Malleson and Andresen 2015), measures based on cell phone usage (Song et al 2019), or estimates derived from satellite imagery (Andresen and Jenion 2008).…”

Section: Explaining Places At High Risk Of Crimementioning

confidence: 99%

Mapping the Risk Terrain for Crime Using Machine Learning

Wheeler

Steenbeek

2020

J Quant Criminol

View full text Add to dashboard Cite

Objectives: We illustrate how a machine learning algorithm, Random Forests, can provide accurate long-term predictions of crime at micro places relative to other popular techniques. We also show how recent advances in model summaries can help to open the 'black box' of Random Forests, considerably improving their interpretability. Methods: We generate long-term crime forecasts for robberies in Dallas at 200 by 200 feet grid cells that allow spatially varying associations of crime generators and demographic factors across the study area. We then show how using interpretable model summaries facilitate understanding the model's inner workings. Results: We find that Random Forests greatly outperform Risk Terrain Models and Kernel Density Estimation in terms of forecasting future crimes using different measures of predictive accuracy, but only slightly outperform using prior counts of crime. We find different factors that predict crime are highly non-linear and vary over space. Conclusions: We show how using black-box machine learning models can provide accurate micro placed based crime predictions, but still be interpreted in a manner that fosters understanding of why a place is predicted to be risky.

show abstract

Section: Explaining Places At High Risk Of Crimementioning

confidence: 99%

Mapping the Risk Terrain for Crime Using Machine Learning

Wheeler

Steenbeek

2020

J Quant Criminol

View full text Add to dashboard Cite

show abstract

“…In it, the structural predictors are often seen through the concentrated disadvantage, ethnic diversity, residential instability of neighbourhoods 7 , 9 , 34 While most of these studies use census data as primary data source, recent years have witnessed a growing interest in alternative data. For example, scholars exploited synthetic social ties to simulate neighbourhood cohesion 35 , and mobility flows to indicate crime opportunities and connections between neighbourhoods 23 . Others leveraged crowd-sourced Point of Interests (POIs), taxi flows 36 , and dynamic population mapping from satellite imagery 17 , 37 and mobile phone activity 14 , 20 to assess the presence of people.…”

Section: Introductionmentioning

confidence: 99%

Socio-economic, built environment, and mobility conditions associated with crime: a study of multiple cities

Nadai

Letouzé

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Nowadays, 23% of the world population lives in multi-million cities. In these metropolises, criminal activity is much higher and violent than in either small cities or rural areas. Thus, understanding what factors influence urban crime in big cities is a pressing need. Seminal studies analyse crime records through historical panel data or analysis of historical patterns combined with ecological factor and exploratory mapping. More recently, machine learning methods have provided informed crime prediction over time. However, previous studies have focused on a single city at a time, considering only a limited number of factors (such as socio-economical characteristics) and often at large in a single city. Hence, our understanding of the factors influencing crime across cultures and cities is very limited. Here we propose a Bayesian model to explore how violent and property crimes are related not only to socio-economic factors but also to the built environmental (e.g. land use) and mobility characteristics of neighbourhoods. To that end, we analyse crime at small areas and integrate multiple open data sources with mobile phone traces to compare how the different factors correlate with crime in diverse cities, namely Boston, Bogotá, Los Angeles and Chicago. We find that the combined use of socio-economic conditions, mobility information and physical characteristics of the neighbourhood effectively explain the emergence of crime, and improve the performance of the traditional approaches. However, we show that the socio-ecological factors of neighbourhoods relate to crime very differently from one city to another. Thus there is clearly no “one fits all” model.

show abstract

“…The repetition of criminal behaviour committed by the same people in the same places is a well-known subject in the theory of hot spots and routine activities (Song et al, 2019;Yao et al, 2020). As a result of analysing historical crime data with data mining techniques, these repetitions can be detected and successful crime prevention policies can be established.…”

Section: Discussionmentioning

confidence: 99%

Big Data, Data Mining, Machine Learning, and Deep Learning Concepts in Crime Data

Güzel¹

2021

JPLC

View full text Add to dashboard Cite

Young adults engage in a disproportionately high rate of problematic behaviors such as risky sexual activities, academic dishonesty, and substance abuse. In order to understand why this occurs, two lesser-known constructs related to risktaking behavior were investigated in this study: differential identification, which has yet to be empirically studied in the context of emerging adults, and criminogenic thinking, which has only been evaluated in this context to a minimal degree. To bridge the gap between these two constructs, motivation was hypothesized to be a moderator in each of these respective relationships. Data from 309 emerging adults were recruited via Amazon's Mechanical Turk (MTurk) to complete the survey materials online. The analysis consisted of a hierarchical multiple linear regression. Results indicated that motivation did not moderate either relationship (i.e., differential identification and risk-taking behavior and criminogenic thinking and risk-taking behavior). However, a main effect was found between one aspect of differential identification and risk-taking behavior. No other main effects were found in this study. Potential explanations for the results of this study are discussed, as well as implications and directions for future research.

show abstract

Crime Feeds on Legal Activities: Daily Mobility Flows Help to Explain Thieves’ Target Location Choices

Cited by 58 publications

References 72 publications

Mapping the Risk Terrain for Crime Using Machine Learning

Mapping the Risk Terrain for Crime Using Machine Learning

Socio-economic, built environment, and mobility conditions associated with crime: a study of multiple cities

Big Data, Data Mining, Machine Learning, and Deep Learning Concepts in Crime Data

Contact Info

Product

Resources

About