Quantity or Spatial Coverage? Using Interpretable Machine Learning to Evaluate the Relationship Between Spatial Strategy of Police Stops and Crime in Crime Hotspots and Non-Hotspots

Abstract

As a result of variations in offender activity patterns in crime hotspots and non-hotspots, the spatial strategies of policing (such as the quantity and spatial coverage) should differ. Existing literature has not examined the spatially heterogeneous effect of police stop strategies on crime. This study focuses on the police stops-crime nexus in China, using the case of a major city’s central district. We introduce the spatial dimension of police stops—spatial coverage—in addition to the commonly considered quantity of police stops. Our results indicate that the spatial coverage of police stops surpasses the number of police stops as the most important crime predictor. We further find spatial heterogeneity in the police stop-crime nexus. A larger amount of police stops and spatially focused stops are more effective in crime hotspots. In crime non-hotspots, higher spatial coverage of police is more important in deterring crime than a larger number of police stops.

Keywords

crime police stops spatial strategy interpretable machine learning models

Get full access to this article

View all access options for this article.

References

Alves

L. G.

Ribeiro

H. V.

Rodrigues

F. A.

(2018). Crime prediction through urban metrics and statistical learning. Physica A: Statistical Mechanics and Its Applications, 505(17), 435–443. https://doi.org/10.1016/j.physa.2018.03.084

Andresen

M. A.

Malleson

(2011). Testing the stability of crime patterns: Implications for theory and policy. Journal of Research in Crime and Delinquency, 48(1), 58–82. https://doi.org/10.1177/0022427810384136

Barr

Pease

(1990). Crime placement, displacement, and deflection. Crime & Justice, 12(1), 277–318. https://doi.org/10.1086/449167

Bowers

K. J.

Johnson

S. D.

(2003). Measuring the geographical displacement and diffusion of benefit effects of crime prevention activity. Journal of Quantitative Criminology, 19(3), 275–301.

Bradford

(2017). Stop and search and police legitimacy. Routledge.

Braga

A. A.

Schnell

(2017). Beyond putting “cops on dots”: Applying theory to advance police responses to crime places. In Unraveling the crime-place connection (22, pp. 261–288). Routledge.

Brantingham

(1993). Nodes, paths, and edges: Considerations on the complexity of crime and the physical environment (1993). In Classics in environmental criminology (pp. 289–326). Routledge.

Brantingham

P. L.

Brantingham

P. J.

(2017). Environment, routine, and situation: Toward a pattern theory of crime. In Routine activity and rational choice (pp. 259–294). Routledge.

Chen

Guestrin

(2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 Aug 13-17. San Francisco, CA, pp. 785, –794.

10.

Cohen

L. E.

Felson

(1979). Social change and crime rate trends: A routine activity approach (1979). In Classics in environmental criminology (pp. 203–232). Routledge.

11.

Cornish

D. B.

Clarke

R. V.

(2014). The reasoning criminal: Rational choice perspectives on offending. Piscataway, NJ: Transaction.

12.

Crow

Bull

(1975). Robbery deterrence: An applied behavioral science demonstration—final report. In Western behavioral science institute. La Jolla.

13.

Durlauf

S. N.

Nagin

D. S.

(2011). Imprisonment and crime: Can both be reduced? Criminology & Public Policy, 10(1), 13–54.

14.

Gonzalez

M. C.

Hidalgo

C. A.

Barabasi

A.-L.

(2008). Understanding individual human mobility patterns. Nature, 453(7196), 779–782.

15.

Groff

E. R.

Ratcliffe

J. H.

Haberman

C. P.

Sorg

E. T.

Joyce

N. M.

Taylor

R. B.

(2015). Does what police do at hot spots matter? The Philadelphia policing tactics experiment. Criminology, 53(1), 23–53. https://doi.org/10.1111/1745-9125.12055

16.

Haberman

C. P.

Ratcliffe

J. H.

(2012). The predictive policing challenges of near repeat armed street robberies. Policing, 6(2), 151–166. https://doi.org/10.1093/police/pas012

17.

Kang

H.-W.

Kang

H.-B.

(2017). Prediction of crime occurrence from multi-modal data using deep learning. PLoS One, 12(4), Article e0176244. https://doi.org/10.1371/journal.pone.0176244

18.

Kelling

G. L.

Pate

Ferrara

Utne

Brown

C. E.

(1981). The Newark foot patrol experiment (pp. 94–96): Police Foundation.

19.

Kelling

G. L.

Pate

Dieckman

Brown

(1974). The Kansas city preventive patrol experiment: A tecnical report: Police Foundation.

20.

Kim

Lee

(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(4), Article 104419. https://doi.org/10.1016/j.scs.2023.104419

21.

Kuhn

H. W.

Tucker

A. W.

(1953). Contributions to the theory of games. Princeton University Press.

22.

(2022). Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost. Computers, Environment and Urban Systems, 96(6), Article 101845. https://doi.org/10.1016/j.compenvurbsys.2022.101845

23.

Liu

(2018). Police legitimacy and compliance with the law among Chinese youth. International Journal of Offender Therapy and Comparative Criminology, 62(11), 3536–3561. https://doi.org/10.1177/0306624X17740559

24.

Lundberg

S. M.

Lee

S.-I.

(2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems.

25.

MacDonald

Fagan

Geller

(2016). The effects of local police surges on crime and arrests in New York City. PLoS One, 11(6), Article e0157223. https://doi.org/10.1371/journal.pone.0157223

26.

Malleson

Andresen

M. A.

(2016). Exploring the impact of ambient population measures on London crime hotspots. Journal of Criminal Justice, 46(3), 52–63. https://doi.org/10.1016/j.jcrimjus.2016.03.002

27.

Marchione

Johnson

S. D.

(2013). Spatial, temporal and spatio-temporal patterns of maritime piracy. Journal of Research in Crime and Delinquency, 50(4), 504–524. https://doi.org/10.1177/0022427812469113

28.

Mousa

S. R.

Bakhit

P. R.

Osman

O. A.

Ishak

(2018). A comparative analysis of tree-based ensemble methods for detecting imminent lane change maneuvers in connected vehicle environments. Transportation Research Record: Journal of the Transportation Research Board, 2672(42), 268–279. https://doi.org/10.1177/0361198118780204

29.

Nagin

D. S.

Solow

R. M.

Lum

(2015). Deterrence, criminal opportunities, and police. Criminology, 53(1), 74–100. https://doi.org/10.1111/1745-9125.12057

30.

Nixon

T. S.

Barnes

(2019). Calibrating student perceptions of punishment: A specific test of general deterrence. American Journal of Criminal Justice, 44(3), 430–456. https://doi.org/10.1007/s12103-018-9466-2

31.

Parkinson

(2011). Crime mapping in a rural community: An examination of hotspots and crime trends. Western Illinois University.

32.

Parsa

A. B.

Movahedi

Taghipour

Derrible

Mohammadian

A. K.

(2020). Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis & Prevention, 136(3), Article 105405. https://doi.org/10.1016/j.aap.2019.105405

33.

Piza

E. L.

Gilchrist

A. M.

(2018). Measuring the effect heterogeneity of police enforcement actions across spatial contexts. Journal of Criminal Justice, 54(1), 76–87. https://doi.org/10.1016/j.jcrimjus.2017.12.007

34.

Pogarsky

Loughran

T. A.

(2016). The policy-to-perceptions link in deterrence: Time to retire the clearance rate’(2016). Criminology & Public Policy, 15(3), 777–790. https://doi.org/10.1111/1745-9133.12241

35.

Ratcliffe

J. H.

(2004). The hotspot matrix: A framework for the spatio‐temporal targeting of crime reduction. Police Practice and Research, 5(1), 5–23. https://doi.org/10.1080/1561426042000191305

36.

Rosenbaum

D. P.

Lurigio

A. J.

(1994). An inside look at community policing reform: Definitions, organizational changes, and evaluation findings. Crime & Delinquency, 40(3), 299–314. https://doi.org/10.1177/0011128794040003001

37.

Rosenfeld

Fornango

(2014). The impact of police stops on precinct robbery and burglary rates in New York City, 2003-2010. Justice Quarterly, 31(1), 96–122. https://doi.org/10.1080/07418825.2012.712152

38.

Rosenfeld

Fornango

(2017). The relationship between crime and stop, question, and frisk rates in New York City neighborhoods. Justice Quarterly, 34(6), 931–951. https://doi.org/10.1080/07418825.2016.1275748

39.

Schnell

Boehme

(2024). Where do cops stop? A new dimension to explore spatial patterns of police contacts. Criminal Justice and Behavior, 51(9), 1320–1338. https://doi.org/10.1177/00938548241249700

40.

Schnell

Cory

Boehme

Hunter

(2024). Where Do Cops Stop? A New Dimension to Explore Spatial Patterns of Police Contacts. Criminal Justice and Behavior, 51(9), 1320–1338.

41.

Smith

D. C.

Purtell

(2008). Does stop and frisk stop crime. annual research conference of the Association of Public Policy and Management, Los Angeles, CA.

42.

Song

Bernasco

Liu

Xiao

Zhou

Liao

(2019). Crime feeds on legal activities: Daily mobility flows help to explain thieves’ target location choices. Journal of Quantitative Criminology, 35(4), 831–854. https://doi.org/10.1007/s10940-019-09406-z

43.

Song

Cai

Liu

Xiao

Yue

(2023). Effects of ambient population with different income levels on the spatio-temporal pattern of theft: A study based on mobile phone big data. Cities, 137(6), Article 104331. https://doi.org/10.1016/j.cities.2023.104331

44.

Song

Liu

Bernasco

Xiao

Zhou

Liao

(2018). Testing indicators of risk populations for theft from the person across space and time: The significance of mobility and outdoor activity. Annals of the Association of American Geographers, 108(5), 1370–1388. https://doi.org/10.1080/24694452.2017.1414580

45.

Taylor

Koper

C. S.

Woods

D. J.

(2011). A randomized controlled trial of different policing strategies at hot spots of violent crime. Journal of Experimental Criminology, 7(2), 149–181. https://doi.org/10.1007/s11292-010-9120-6

46.

Weisburd

(2015). The law of crime concentration and the criminology of place. Criminology, 53(2), 133–157. https://doi.org/10.1111/1745-9125.12070

47.

Weisburd

Petersen

Telep

C. W.

Fay

S. A.

(2024). Can increasing preventive patrol in large geographic areas reduce crime? A systematic review and meta-analysis. Criminology & Public Policy.

48.

Weisburd

Telep

C. W.

Lawton

B. A.

(2014). Could innovations in policing have contributed to the New York City crime drop even in a period of declining police strength? The case of stop, question and frisk as a hot spots policing strategy. Justice Quarterly, 31(1), 129–153. https://doi.org/10.1080/07418825.2012.754920

49.

Weisburd

Wooditch

Weisburd

Yang

S. M.

(2016). Do stop, question, and frisk practices deter crime? Evidence at microunits of space and time. Criminology & Public Policy, 15(1), 31–56. https://doi.org/10.1111/1745-9133.12172

50.

White

M. D.

Fradella

H. F.

(2016). Stop and frisk: The use and abuse of a controversial policing tactic. In Stop and frisk. New York University Press.

51.

Xiao

Liu

Zhou

(2021). Nonlinear and synergistic effects of TOD on urban vibrancy: Applying local explanations for gradient boosting decision tree. Sustainable Cities and Society, 72(9), Article 103063. https://doi.org/10.1016/j.scs.2021.103063

52.

Yang

Chen

Yuan

(2021). The application of XGBoost and SHAP to examining the factors in freight truck-related crashes: An exploratory analysis. Accident Analysis & Prevention, 158(10), Article 106153. https://doi.org/10.1016/j.aap.2021.106153

53.

Zhang

Liu

Lan

Song

Xiao

Chen

(2022). Interpretable machine learning models for crime prediction. Computers, Environment and Urban Systems, 94(4), Article 101789. https://doi.org/10.1016/j.compenvurbsys.2022.101789