To advance the interpretability of machine learning for long-term crime prediction in China, we compared the performance of multiple machine learning algorithms in predicting the spatial pattern of theft in Beijing. Gradient boosting decision tree emerged as the algorithm with best predictive accuracy. After identifying the importance of criminogenic features, we extended the interpreter SHAP to reveal nonlinear and spatially heterogeneous associations between environmental features and theft and we summarized six relation types of such associations at the global scale. At the local scale, we clustered six area types according to the contribution of environmental attributes to theft prediction in each grid. Policy makers should adopt place-based crime prevention measures based on the specific type of each grid belongs to.
AlvesL. G. A.RibeiroH. V.RodriguesF. A. (2018). Crime prediction through urban metrics and statistical learning. Physica A, 505, 435–443.
2.
ArnioA. N. (2021). Examining the effects of neighborhood contextual factors on officer-involved shootings. Justice Quarterly, 38(4), 626–652.
3.
BarnumJ. D.CaplanJ. M.KennedyL. W.PizaE. L. (2017). The crime kaleidoscope: A cross-jurisdictional analysis of place features and crime in three urban environments. Applied Geography, 79, 203–211.
4.
BernascoW.BlockR. (2011). Robberies in Chicago: A block-level analysis of the influence of crime generators, crime attractors, and offender anchor points. Journal of Research in Crime and Delinquency, 48(1), 33–57.
5.
BlockS.FujitaS. (2013). Patterns of near repeat temporary and permanent motor vehicle thefts. Crime Prevention and Community Safety, 15(2), 151–167.
6.
BoessenA.HippJ. R. (2018). Parks as crime inhibitors or generators: Examining parks and the role of their nearby context. Social Science Research, 76, 186–201.
7.
BoivinR. (2018). Routine activity, population(s) and crime: Spatial heterogeneity and conflicting propositions about the neighborhood crime-population link. Applied Geography, 95, 79–87.
8.
BragaA. A.ClarkeR. V. (2014). Explaining high-risk concentrations of crime in the city: Social disorganization, crime opportunities, and important next steps. Journal of Research in Crime and Delinquency, 51(4), 480–498.
9.
BragaA. A.WeisburdD. (2010). Policing problem places: Crime hot spots and effective prevention. Oxford University Press.
10.
BrantinghamP. L.BrantinghamP. J. (1993). Nodes, paths and edges: Considerations on the complexity of crime and the physical environment. Journal of Environmental Psychology, 13(1), 3–28.
11.
BrowningC. R.ByronR. A.CalderC. A.KrivoL. J.KwanM. P.LeeJ. Y.PetersonR. D. (2010). Commercial density, residential concentration, and crime: Land use patterns and violence in neighborhood context. Journal of Research in Crime and Delinquency, 47(3), 329–357.
12.
BrowningC. R.JacksonA. L. (2013). The social ecology of public space: Active streets and violent crime in urban neighborhoods. Criminology, 51(4), 1009–1043.
13.
CahillM.MulliganG. (2007). Using geographically weighted regression to explore local crime patterns. Social Science Computer Review, 25(2), 174–193.
14.
CaplanJ. M.KennedyL. W.MillerJ. (2011). Risk terrain modeling: Brokering criminological theory and GIS methods for crime forecasting. Justice Quarterly, 28(2), 360–381.
15.
CaplanJ. M.KennedyL. W.PizaE. L. (2013). Joint utility of event-dependent and environmental crime analysis techniques for violent crime forecasting. Crime and Delinquency, 59(2), 243–270.
16.
ChaineyS.TompsonL.UhligS. (2008). The utility of hotspot mapping for predicting spatial patterns of crime. Security Journal, 21, 4–28.
17.
ChenJ.LiuL.XiaoL.XuC.LongD. (2020). Integrative analysis of spatial heterogeneity and overdispersion of crime with a geographically weighted negative binomial model. International Journal of Geo-Information, 9(1), 60.
18.
CohenL. E.FelsonM. (1979). Social change and crime rate trends: A routine activity approach. American Sociological Review, 44(4), 588–608.
19.
DemeauE.ParentG. (2018). Impacts of crime attractors and generators on criminality in Montreal. Canadian Journal of Criminology and Criminal Justice, 60(3), 387–412.
20.
DrawveG. (2016). A metric comparison of predictive hot spot techniques and RTM. Justice Quarterly, 33(3), 369–397.
21.
EkblomP. (2011). Crime prevention, security and community safety using the 5Is framework. Palgrave Macmillan.
22.
GraifC.SampsonR. J. (2009). Spatial heterogeneity in the effects of immigration and diversity on neighborhood homicide rates. Homicide Studies, 13(3), 242–260.
23.
GreenJ. W. (2022). The built environment and predicting child maltreatment: An application of random forests to risk terrain modeling. The Professional Geographer, 74(1), 67–78.
24.
HeZ.WangZ.XieZ.WuL.ChenZ. (2022). Multiscale analysis of the influence of street built environment on crime occurrence using street-view images. Computers, Environment and Urban Systems, 97(3), 101865.
25.
JiS.WangX.LyuT.LiuX.WangY.HeinenE.SunZ. (2022). Understanding cycling distance according to the prediction of the XGBoost and the interpretation of SHAP: A non-linear and interaction effect analysis. Journal of Transport Geography, 103, 103414.
26.
JonesR. W.PridemoreW. A. (2019). Toward an integrated multilevel theory of crime at place: Routine activities, social disorganization, and the law of crime concentration. Journal of Quantitative Criminology, 35(3), 543–572.
27.
KennedyL. W.CaplanJ. M.PizaE. (2011). Risk clusters, hotspots, and spatial intelligence: Risk terrain modeling as an algorithm for police resource allocation strategies. Journal of Quantitative Criminology, 27, 339–362.
28.
KennedyL. W.CaplanJ. M.PizaE. L.Buccine-SchraederH. (2016). Vulnerability and exposure to crime: Applying risk terrain modeling to the study of assault in Chicago. Applied Spatial Analysis and Policy, 9, 529–548.
29.
KimS.LeeS. (2023). Nonlinear relationships and interaction effects of an urban environment on crime incidence: Application of urban big data and an interpretable machine learning method. Sustainable Cities and Society, 91, 104419.
30.
LiuL. (2022). Progresses and challenges of crime geography and crime analysis. In LiB.ShiX.ZhuA.WangC.LinH. (Eds.) New thinking in GIScience (pp. 349–353). Springer.
31.
LouderbackE. R.Sen RoyS. (2018). Integrating social disorganization and routine activity theories and testing the effectiveness of neighbourhood crime watch programs: Case study of Miami-Dade county, 2007–15. The British Journal of Criminology, 58(4), 968–992.
32.
LundbergS.LeeS.-I. (2017). A unified approach to interpreting model predictions [Conference session]. Proceedings of the 31st International Conference on Neural Information Processing Systems (pp.4768–4777).
33.
LundbergS. M.ErionG. G.LeeS. I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv 2018, arXiv: 1802.03888.
34.
LvY.LanZ.KanC.ZhengX. (2021). Polycentric urban development and its determinants in China: A geospatial big data perspective. Geographical Analysis, 53(3), 520–542.
RatcliffeJ. H.RengertG. F. (2008). Near-repeat patterns in Philadelphia shootings. Security Journal, 21, 58–76.
37.
RiceK. J.MithW. R. (2002). Socioecological models of automotive theft: Integrating routine activity and social disorganization approaches. Journal of Research in Crime and Delinquency, 39(3), 304–336.
38.
RummensA.HardynsW.PauwelsL. (2017). The use of predictive analysis in spatiotemporal crime forecasting: Building and testing a model in an urban context. Applied Geography, 86, 255–261.
39.
SampsonR. J.GrovesW. B. (1989). Community structure and crime: Testing social-disorganization theory. American Journal of Sociology, 94(4), 774–802.
40.
SampsonR. J.RaudenbushS. W.EarlsF. (1997). Neighborhoods and violent crime: A multilevel study of collective efficacy. Science, 277(5328), 918–924.
41.
ShapleyL. S. (1953). A value for n-person games. Contributions to the Theory of Games, 2(28), 307–317.
42.
SongG.BernascoW.LiuL.XiaoL.ZhouS.LiaoW. (2019). Crime feeds on legal activities: Daily mobility flows help to explain thieves’ target location choices. Journal of Quantitative Criminology, 35(4), 831–854.
43.
SongG.ZhangY.BernascoW.CaiL.LiuL.QinB.ChenP. (2023). Residents, employees and visitors: Effects of three types of ambient population on theft on weekdays and weekends in Beijing, China. Journal of Quantitative Criminology, 39(2), 385–423.
44.
StuckyT. D.SmithS. L. (2017). Exploring the conditional effects of bus stops on crime. Security Journal, 30, 290–309.
45.
TaylorR. B.RatcliffeJ. H.PerenzinA. (2015). Can we predict long-term community crime problems? The estimation of ecological continuity to model risk heterogeneity. Journal of Research in Crime and Delinquency, 52(5), 635–657.
46.
WeisburdD. (2015). The law of crime concentration and the criminology of place. Criminology, 53(2), 133–157.
47.
WellsW.WuL.YeX. (2012). Patterns of near-repeat gun assaults in Houston. Journal of Research in Crime and Delinquency, 49(2), 186–212.
48.
WheelerA. P.SteenbeekW. (2021). Mapping the risk terrain for crime using machine learning. Journal of Quantitative Criminology, 37(2), 445–480.
49.
WheelerD. C.WallerL. A. (2009). Comparing spatially varying coefficient models: A case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests. Journal of Geographical Systems, 11(1), 1–22.
50.
WilsonJ. Q.KellingG. L. (1982). Broken windows. Atlantic Monthly, 249(3), 29–38.
51.
XinY.CaiT. (2020). Paying money for freedom: Effects of monetary compensation on sentencing for criminal traffic offenses in China. Journal of Quantitative Criminology, 36(1), 1–28.
52.
ZhangL.MessnerS. F.LiuJ. (2007). An exploration of the determinants of reporting crime to the police in the city of Tianjin, China. Criminology, 45(4), 959–984.
53.
ZhangX.LiuL.LanM.SongG.XiaoL.ChenJ. (2022). Interpretable machine learning models for crime prediction. Computers, Environment and Urban Systems, 94, 101789.
54.
ZhangX.LiuL.XiaoL.JiJ. (2020). Comparison of machine learning algorithms for predicting crime hotspots. IEEE Access, 8, 181302–181310.
55.
ZhangY.CaiL.SongG.LiuL.ZhuC. (2022). From residential neighborhood to activity space: The effects of educational segregation on crime and their moderation by social context. Annals of the American Association of Geographers, 112(8), 2393–2412.
56.
ZhuoY.MessnerS. F.ZhangL. (2008). Criminal victimization in contemporary China: A review of the evidence and challenges for future research. Crime Law and Social Change, 50(3), 197–209.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
