Once Upon a Crime

Bogomolov, Andrey; Lepri, Bruno; Staiano, Jacopo; Oliver, Núria; Pianesi, Fabio; Pentland, Alex

doi:10.1145/2663204.2663254

Cited by 208 publications

(65 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our use of mobile phone locations diverges from how prior studies on crime in London (Bogomolov et al 2014) and in Osaka, Japan (Hanaoka 2018) have used such data in research on crime. These prior studies used mobile phone users' locations as a measure of how many people were present at a specific location at a specific day or time, which has been referred to as the size of the ambient population or the actual population at risk.…”

Section: Calculation Of Mobility Streamsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

Objective According to routine activity theory and crime pattern theory, crime feeds on the legal routine activities of offenders and unguarded victims. Based on this assumption, the present study investigates whether daily mobility flows of the urban population help predict where individual thieves commit crimes. Methods Geocoded tracks of mobile phones are used to estimate the intensity of population mobility between pairs of 1616 communities in a large city in China. Using data on 3436 police-recorded thefts from the person, we apply discrete choice models to assess whether mobility flows help explain where offenders go to perpetrate crime. Results Accounting for the presence of crime generators and distance to the offender's home location, we find that the stronger a community is connected by population flows to where the offender lives, the larger its probability of being targeted. Conclusions The mobility flow measure is a useful addition to the estimated effects of distance and crime generators. It predicts the locations of thefts much better than the presence of crime generators does. However, it does not replace the role of distance, suggesting that offenders are more spatially restricted than others, or that even within their activity spaces they prefer to offend near their homes.

show abstract

Section: Calculation Of Mobility Streamsmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Andresen and Malleson 2011). Finally, mobile phone data are becoming a popular means of estimating pedestrian flows, and some preliminary research has attempted to use these data to improve crime estimates (Bogomolov et al 2014). However, as mobile telephone data are privately owned they can be extremely difficult to access for research purposes and pose a number of ethical questions, particularly around privacy and informed consent.…”

Section: The Population At Risk In Crime Analysismentioning

confidence: 99%

Spatio-temporal crime hotspots and the ambient population

2015

View full text Add to dashboard Cite

It is well known that, due to that inherent differences in their underlying causal mechanisms, different types of crime will have variable impacts on different groups of people. Furthermore, the locations of vulnerable groups of people are highly temporally dynamic. Hence an accurate estimate of the true population at risk in a given place and time is vital for reliable crime rate calculation and hotspot generation. However, the choice of denominator is fraught with difficulty because data describing popular movements, rather than simply residential location, are limited. This research will make use of new 'crowd-sourced' data in an attempt to create more accurate estimates of the population at risk for mobile crimes such as street robbery. Importantly, these data are both spatially and temporally referenced and can therefore be used to estimate crime rate significance in both space and time. Spatio-temporal cluster hunting techniques will be used to identify crime hotspots that are significant given the size of the ambient population in the area at the time.

show abstract

“…Space and time as well as previous violence were used as inputs to the model. Other machine learning approaches have been applied to predicting individual violence using social media or mobile device use [1,6,17]. The inclusion of social media data is only possible over recent time frames and in developed countries where such usage is pervasive.…”

Section: Introductionmentioning

confidence: 99%

Spatio-temporal violent event prediction using Gaussian process regression

Kupilik

Witmer

2018

J Comput Soc Sc

View full text Add to dashboard Cite

Large volume, data-driven violent conflict research is now possible using publicly available data sets. This work analyzes the predictive ability of data-derived Gaussian process models compared to a generalized linear model. Societal violence is a highly nonlinear process and the available data sets have high dimensionality that yield observation totals in the hundreds of thousands to millions. These challenges make machine learning modeling difficult without significant dimensionality reduction. We develop a computationally intensive Gaussian process modeling approach that exploits the size and complexity of the violent conflict dataset to identify appropriate basis vectors for the model. We develop our models using gridded monthly violent event counts for sub-Saharan Africa from 1980 to 2012. Our resulting Gaussian process models modestly improve the accuracy and predictive ability of existing generalized linear models. Despite this improvement, the accurate prediction of violence in sub-Saharan Africa at a relatively fine resolution spatial grid of 1 • latitude/longitude remains a challenging problem.

show abstract

Once Upon a Crime

Cited by 208 publications

References 45 publications

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

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

Spatio-temporal crime hotspots and the ambient population

Spatio-temporal violent event prediction using Gaussian process regression

Contact Info

Product

Resources

About