In recent years, the field of crime prediction has drawn increasing attention in Japan. However, predicting crime in Japan is especially challenging because the crime rate is considerably lower than that of other developed countries, making the development of a statistical model for crime prediction quite difficult. Risk terrain modeling (RTM) may be the most suitable method, as it depends mainly on the environmental factors associated with crime and does not require past crime data. In this study, we applied RTM to cases of theft from vehicles in Fukuoka, Japan, in 2014 and evaluated the predictive performance (hit rate and predictive accuracy index) in comparison to other crime prediction techniques, including KDE, ProMap, and SEPP, which use past crime occurrences to predict future crime. RTM was approximately twice as effective as the other techniques. Based on the results, we discuss the merits of and drawbacks to using RTM in Japan.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
According to United Nations Office on Drugs and Crime (UNODC) statistics (https://data.unodc.org/), the number of police-recorded offenses per 100,000 people in the US and Japan in 2014 are as follows: for theft, 1818.46 vs. 356.20; for burglary, 536.28 vs. 73.79; for assault, 228.86 vs. 21.02; for robbery, 101.08 vs. 2.41; for rape, 36.95 vs. 0.99; and for intentional homicide, 4.43 vs. 0.31.
While we do not discuss them here, we can find important studies that discuss the complexities of and tips for operationalizing hotspots in GIS (e.g., Chainey and Ratcliffe 2013; Eck et al. 2005). Other research discusses various techniques available for operationalization of hotspots (e.g., Haberman 2017). Crime prediction studies rely on this research, and thus the two are closely related.
Original data were downloaded from Fukuoka Prefectural Police Department’s homepage (http://www.police.pref.fukuoka.jp/data/open/cnt/3/1469/1/H27City.pdf), Tokyo Metropolitan Police Department’s homepage (http://www.keishicho.metro.tokyo.jp/about_mpd/jokyo_tokei/jokyo/ninchikensu.html) and the FBI’s Uniform Crime Reporting website (https://ucr.fbi.gov/crime-in-the-u.s/2015/crime-in-the-u.s.-2015/resource-pages/downloads/download-printable-files); the rates were then calculated.
We should be cautious when dealing with crime data since under-reported occurrences are always present. Although we cannot know whether current data from Fukuoka city omit these potential victimizations, we can show how much underreporting is present in Japan. According to the fourth National Crime Victimization Survey (https://www.npa.go.jp/hanzaihigai/whitepaper/w-2013/html/gaiyou/part2/s2_4c5.html), in Japan in 2014, 29.5% of VLT (excluding N.A.s) were not reported to the police.
Adepeju, M., Rosser, G., & Cheng, T. (2016). Novel evaluation metrics for sparse spatio-temporal point process hotspot predictions-a crime case study. International Journal of Geographical Information Science, 30(11), 1–22.
Anselin, L., Cohen, J., Cook, D., Gorr, W., & Tita, G. (2000). Spatial analyses of crime. Criminal Justice, 4(2), 213–262.
Block, C. (1995). STAC hot-spot areas: A statistical tool for law enforcement decisions. In Crime analysis through computer mapping (pp. 15–32). Washington, DC: Police Executive Research Forum.
Block, R., & Block, C. (1995). Space, place and crime: Hot spot areas and hot places of liquor-related crime. In J. Eck & D. Weisburd (Eds.), Crime and place (pp. 145–183). Monsey: Criminal Justice Press.
Bowers, K., Johnson, S., & Pease, K. (2004). Prospective hot-spotting: the future of crime mapping? British Journal of Criminology, 44(5), 641–658.
Brantingham, P., & Brantingham, P. (1995). Criminality of place: Crime generators and crime attractors. European Journal on Criminal Policy and Research, 3(3), 1–26.
Cabinet Secretariat (2014). Action Plan on Promoting Utilization of Geospatial Information: Summary by Measures (G-Space Action Plan), Geospatial Information Utilization Promotion Meeting. http://www.cas.go.jp/jp/seisaku/sokuitiri/260617/gaiyou03.pdf. Accessed 16 February 2017. (In Japanese).
Caplan, J., & Kennedy, L. (2016). Risk terrain modeling: Crime prediction and risk reduction. Oakland: University of California Press.
Caplan, J., Kennedy, L., & Miller, J. (2011). Risk terrain modeling: Brokering criminological theory and GIS methods for crime forecasting. Justice Quarterly, 28(2), 360–381.
Caplan, J., Kennedy, L., & Piza, E. (2013). Risk terrain modeling diagnostics utility (version 1.0). Newark: Rutgers Center on Public Security.
Chainey, S. (2005). Methods and techniques for understanding crime hot spots. In Mapping crime: Understanding hot spots (pp. 15–34). US Department of Justice.
Chainey, S., & Ratcliffe, J. (2013). GIS and crime mapping. Chichester: Wiley.
Chainey, S., Tompson, L., & Uhlig, S. (2008). The utility of hotspot mapping for predicting spatial patterns of crime. Security Journal, 21(1), 4–28.
Cheng, T., & Adepeju, M. (2013). Detecting emerging space-time crime patterns by prospective STSS. In Proceedings of the 12th international conference on geocomputation. http://www.geocomputation.org/2013/papers/77.pdf. Accessed 22 August 2017.
CIVITAS. (2012). Comparisons of Crime in OECD Countries. http://www.civitas.org.uk/content/files/crime_stats_oecdjan2012.pdf. Accessed 22 August 2017.
Dugato, M. (2013). Assessing the validity of risk terrain modeling in a European city: Preventing robberies in the city of Milan. Crime Mapping, 5(1), 63–89.
Drawve, G. (2014). A metric comparison of predictive hot spot techniques and RTM. Justice Quarterly, 33(3), 369–397.
Eck, J., Chainey, S., Cameron, J., & Wilson, R. (2005). Mapping crime: Understanding hotspots. Washington, D.C.: National Institute of Justice.
Fox, J., & Brown, D. (2012). Using temporal indicator functions with generalized linear models for spatial-temporal event prediction. Procedia Computer Science, 8, 106–111.
Gorr, W., & Harries, R. (2003). Introduction to crime forecasting. International Journal of Forecasting, 19(4), 551–555.
Groff, E., & La Vigne, N. (2002). Forecasting the future of predictive crime mapping. Crime Prevention Studies, 13, 29–57.
Haberman, C. (2017). Overlapping Hot Spots? Criminology & Public Policy, 16(2), 633–660.
Hart, T., & Zandbergen, P. (2012). Effects of data quality on predictive hotspot mapping: Final technical report (doc. #239861). Washington, D.C.: National Institute of Justice.
Johnson, S., Birks, D., McLaughlin, L., Bowers, K., & Pease, K. (2007). Prospective crime mapping in operational context, final report. London: Home Office.
Johnson, S., Bowers, K., Birks, D., & Pease, K. (2009). Predictive mapping of crime by ProMap: Accuracy, units of analysis, and the environmental backcloth. In D. Weisburd, W. Bernasco, & G. J. N. Bruinsma (Eds.), Putting crime in its place (pp. 171–198). New York: Springer.
Johnson, S., Summers, L., & Pease, K. (2006). Vehicle crime: Communicating spatial and temporal patterns, final report. London: Home Office.
Kennedy, L., Caplan, J., & Piza, E. (2011). Risk clusters, hotspots, and spatial intelligence: Risk terrain modeling as an algorithm for police resource allocation strategies. Journal of Quantitative Criminology, 27(3), 339–362.
Kikuchi, G., Amemiya, M., Shimada, T., Saito, T., & Harada, Y. (2010). An analysis of near repeat victimization patterns across crime types―an application of Spatio-temporal K function―. Theory and Applications of GIS, 18(2), 129–138 (In Japanese).
Kulldorff, M., Athas, W., Feurer, E., Miller, B., & Key, C. (1998). Evaluating cluster alarms: A space-time scan statistic and brain cancer in Los Alamos, New Mexico. American Journal of Public Health, 88(9), 1377–1380.
Kulldorff, M., Heffernan, R., Hartman, J., Assunção, R., & Mostashari, F. (2005). A space–time permutation scan statistic for disease outbreak detection. PLoS Medicine, 2(3), 216–224.
Levine, N. (2008). The “hottest” part of a hotspot: Comments on “the utility of hotspot mapping for predicting spatial patterns of crime”. Security Journal, 21(4), 295–302.
Mohler, G. (2014). Marked point process hotspot maps for homicide and gun crime prediction in Chicago. International Journal of Forecasting, 30(3), 491–497.
Mohler, G. (2015). Event forecasting system. U. S. Patent 13,676,358. 3 February 2015.
Mohler, G., Short, M., Brantingham, P., Schoenberg, F., & Tita, G. (2011). Self-exciting point process modeling of crime. Journal of the American Statistical Association, 106(493), 100–108.
Moreto, W., & Caplan, J. M. (2010). Forecasting global maritime piracy utilizing the risk terrain modeling (rtm) approach. Rutgers center on public security brief.
Moreto, W. D., Piza, E. L., & Caplan, J. M. (2014). “A plague on both your houses?”: Risks, repeats and reconsiderations of urban residential burglary. Justice Quarterly, 31(6), 1102–1126.
Nagasawa, H., & Hosoe, T. (1999). A study on the factors of criminal situations of thefts from cars. Bulletin of the Faculty of Social Welfare, Iwate Prefectural University, 61–72. (In Japanese).
Ohyama, T., Amemiya, M., Shimada, T., & Nakaya, T. (2017). Recent research trends on geographical crime prediction. Theory and Applications of GIS, 25(1), 33–43 (In Japanese).
Onat, I., & Gul, Z. (2018). Terrorism Risk Forecasting by Ideology. European Journal on Criminal Policy and Research, 1–17.
Openshaw, S. (1995). Developing automated and smart spatial pattern exploration tools for geographical information systems applications. Journal of the Royal Statistical Society. Series D (The Statistician), 44(1), 3–16.
Openshaw, S., Charlton, M., Wymer, C., & Craft, A. (1987). A mark 1 geographical analysis machine for the automated analysis of point data sets. International Journal of Geographical Information System, 1(4), 335–358.
Perry, W., McInnis, B., Price, C., Smith, S., & Hollywood, J. (2013). Predictive policing: The role of crime forecasting in law enforcement operations. Santa Monica: Rand Corporation.
Ratcliffe J. (1999). Hotspot detective for MapInfo helpfile version 1.0.
Roberts, A. (2008). The influences of incident and contextual characteristics on crime clearance of nonlethal violence: A multilevel event history analysis. Journal of Criminal Justice, 36(1), 61–71.
Roberts, A., & LaFree, G. (2004). Explaining Japan’s postwar violent crime trends. Criminology, 42(1), 179–210.
Rosser, G., & Cheng, T. (2016). Improving the robustness and accuracy of crime prediction with the self-exciting point process through isotropic triggering. Applied Spatial Analysis and Policy, 1–21.
Rosser, G., Davies, T., Bowers, K. J., Johnson, S., & Cheng, T. (2017). Predictive crime mapping: Arbitrary grids or street networks? Journal of Quantitative Criminology, 33(3), 569–594.
Sherman, L. (1995). Hot spots of crime and criminal careers of places. In J. Eck & D. Weisburd (Eds.), Crime and place: Crime prevention studies (pp. 35–52). Monsey: Criminal Justice Press.
Sherman, L., Gartin, P., & Buerger, M. (1989). Hot spots of predatory crime: Routine activities and the criminology of place. Criminology, 27(1), 27–56.
Shiode, S. (2011). Street-level spatial scan statistic and STAC for Analysing street crime concentrations. Transactions in GIS, 15(3), 365–383.
Shiode, S., & Shiode, N. (2014). Microscale prediction of near-future crime concentrations with street-level Geosurveillance. Geographical Analysis, 46(4), 435–455.
Thakali, L., Kwon, T. J., & Fu, L. (2015). Identification of crash hotspots using kernel density estimation and kriging methods: A comparison. Journal of Modern Transportation, 23(2), 93–106.
Townsley, M., Homel, R., & Chaseling, J. (2003). Infectious burglaries. A test of the near repeat hypothesis. British Journal of Criminology, 43(3), 615–633.
Van Patten, I., McKeldin-Coner, J., & Cox, D. (2009). A Microspatial analysis of robbery: Prospective hot spotting in a Small City. Crime Mapping: A Journal of Research and Practice, 1(1), 7–32.
Wang, X., & Brown, D. (2012). The spatio-temporal modeling for criminal incidents. Security Informatics, 1(1), 1–17.
The data on crime was provided to us under the Fukuoka Prefectural Police’s Crime Prevention Research Advisor framework; we would like to thank the Fukuoka Prefectural Police for their support. We would also like to thank Dr. Millar for English language editing.
This study was funded by a grant from the Nikkoso Research Foundation for Safe Society in 2016 and JSPS Grant Number JP17H02046.
Conflict of Interest
The authors declare that they have no conflict of interest.
Description for ProMap
where τ is the spatial bandwidth, ν is the temporal bandwidth, ci is the number of cells between each location of crime i within the spatial, ei is the time elapsed for each occurrence time of crime i within the temporal bandwidth bandwidth and the cell.
To obtain ci in Eq. 1.1, as shown in Fig. 4, a plurality of concentric circles (radius 12.5 m + 25 m*n, where n = 0, 1, 2, …, 10) were drawn. Although the radius of the largest circle is 262.5 m at the maximum, 250 m was set as the upper limit in order to exclude points outside of it. Equal weighting was given to the points existing within the same distance range (as shown in Fig. 4, X1 = 0, X2 = 1, X3 = 2). As in previous studies (Bowers et al. 2004; Johnson et al. 2007, 2009), the number of weeks from the date of occurrence was used for ei. The number of days was divided by 7; no rounding was performed.
Description for SEPP
For SEPP, the prediction was carried out using Eq. 1.2 with reference to a series of studies by Mohler (Mohler et al. 2011; Mohler 2014, 2015). The intensity of crime in a location (x,y) on date (t) is described as:
where t-tk is the numbers of dates between a prediction target period and each occurrence date of a crime event, x-xk, y-yk are the instance between each target cell and each crime event.
In these equations, pij indicates the probability of event i (offspring) being triggered by another event j (parent). These i and j events are called triggering pairs. Additionally, pbij is defined as the probability that event i occurs independently from other events. Thus, i is called a background event (equal to the parent events). We divided events into triggering pairs and background events using the EM algorithm described by Rosser and Cheng (2016). First, we set initial values of pij following Eq. 1.8 (here, we set α as 1.5 and β as 500) and obtained the probability matrix P0 (upper triangular matrix). Based on those values, we distinguished parents and their offspring.
We then calculated parameters following Eqs. 1.5–1.11. The ω and σ2 were computed using triggering pairs. Once we obtained the parameters, we updated pij following Eq. 1.11 and repeated these steps until ||Pn-Pn-1|| was smaller than 1 × 10−7.
About this article
Cite this article
Ohyama, T., Amemiya, M. Applying Crime Prediction Techniques to Japan: A Comparison Between Risk Terrain Modeling and Other Methods. Eur J Crim Policy Res 24, 469–487 (2018). https://doi.org/10.1007/s10610-018-9378-1
- Crime prediction
- Crime mapping
- Risk terrain modeling
- Self-exciting point process
- Prospective mapping