Spatiotemporal Crime Hotspot Detection in Chicago Using the Spatial-temporal Density-based Spatial Clustering of Applications with Noise (ST-DBSCAN) Clustering Algorithm

Authors

  • Payman Othman Rahem Computer Science Department, College of Base Education, University of Sulaimani, Sulaimani, Iraq

DOI:

https://doi.org/10.25098/10.1.36

Keywords:

ST-DBSCAN, spatiotemporal clustering, crime hotspot detection, Chicago crime data, density-based clustering, crime pattern recognition, cluster validation

Abstract

The paper uses ST-DBSCAN (Spatiotemporal Density-Based Spatial Clustering of Applications with Noise) to examine the crime patterns in Chicago with 220,723 reported crimes in 2025. The analysis combines both spatial and temporal dimensions to establish the existence of persistent crime hotspots and defines them as to geographic distribution, spatial scale and the dynamics of time. The findings provide practical insight for law enforcement agencies to help guide allocation and prevention of crime.

The year-round analysis has found 16 significant spatiotemporal clusters (excluding Cluster 0, which is a diffuse city-wide background signature, not a localized hot spot). Battery and theft are the most prevalent types of crime in clusters, and criminal damage and deceptive practice are present in certain clusters. The algorithm was set with epsilon1 = 0.5 km, epsilon2 = 24 hours, and minPts = 20 with the resultant noise rate of 0.35% which means that almost all events belong to meaningful clusters. The internal validation provides a Silhouette Score of -0.15 and a Davies-Bouldin Index of 4.37 indicating the overlapping, non-spherical nature of the urban crime patterns. Temporal holdout validation, training on the first 70% of 2025, and testing on the last 30% - has a hit rate of 32.8, which confirms meaningful predictive consistency. The stability of the clusters with respect to changes of the parameters is confirmed by the sensitivity analysis where the values of Adjusted Rand Index (ARI) are between 0.11 and 0.37.

The results add to the existing body of research on crime analytics and indicate the usefulness of spatiotemporal clustering as an instrument to manage urban public safety.

References

S. Chainey and J. Ratcliffe, GIS and Crime Mapping. London, UK: Wiley, 2005.

P. Brantingham and P. Brantingham, "Criminality of place: Crime generators and crime attractors," European Journal on Criminal Policy and Research, vol. 3, no. 3, pp. 5–26, 1995.

L. E. Cohen and M. Felson, "Social change and crime rate trends: A routine activity approach," American Sociological Review, vol. 44, no. 4, pp. 588–608, 1979.

J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 4th ed. Burlington, MA: Morgan Kaufmann, 2023.

M. Ester, H. P. Kriegel, J. Sander, and X. Xu, "A density-based algorithm for discovering clusters in large spatial databases with noise," in Proc. 2nd Int. Conf. Knowledge Discovery and Data Mining, Portland, OR, 1996, pp. 226–231.

L. W. Kennedy, J. M. Caplan, and E. Piza, "Risk clusters, hotspots, and spatial intelligence: Risk terrain modeling as an algorithm for police resource allocation strategies," Journal of Quantitative Criminology, vol. 27, no. 3, pp. 339–362, 2011.

J. Liu, H. Qin, Z. Liu, S. Wang, Q. Zhang, and Z. He, "A density-based spatial clustering of application with noise algorithm and its empirical research," Highlights in Science, Engineering and Technology, vol. 7, pp. 174–179, Aug. 2022, doi:10.54097/hset.v7i.1054.

D. Birant and A. Kut, "ST-DBSCAN: An algorithm for clustering spatial-temporal data," Data & Knowledge Engineering, vol. 60, no. 1, pp. 208–221, 2007.

H. Wang, H. Zheng, and B. Wu, "Spatiotemporal characteristics of urban traffic congestion: A case study based on taxi GPS data," IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 4, pp. 2106–2118, 2021.

T. Nakaya and K. Yano, "Visualising crime clusters in a space-time cube: An exploratory data-analysis approach using space-time kernel density estimation and scan statistics," Transactions in GIS, vol. 14, no. 3, pp. 223–239, 2010.

J. E. Eck, S. Chainey, J. G. Cameron, M. Leitner, and R. E. Wilson, Mapping Crime: Understanding Hot Spots. Washington, DC, USA: National Institute of Justice, 2005.

M. A. Tayebi, M. Ester, U. Glasser, and P. L. Brantingham, "CRIMETRACER: Activity space based crime location prediction," in Proc. IEEE/ACM Int. Conf. Advances in Social Networks Analysis and Mining, Niagara Falls, ON, 2014, pp. 472–480.

Z. He, R. Lai, Z. Wang, H. Liu, and M. Deng, "Comparative study of approaches for detecting crime hotspots with considering concentration and shape characteristics," International Journal of Environmental Research and Public Health, vol. 19, no. 21, 2022.

K. Lewenhagen et al., "A globally optimal algorithm for hotspot detection and ranking," Crime Science, 2026.

E. Schubert, J. Sander, M. Ester, H. P. Kriegel, and X. Xu, "DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN," ACM Transactions on Database Systems, vol. 42, no. 3, pp. 1–21, 2017.

E. Cesario, P. Lindi, and A. Vinci, "Multi-density crime predictor: An approach to forecast criminal activities in multi-density crime hotspots," Journal of Big Data, vol. 11, 2024.

Published

2026-07-26

How to Cite

Othman Rahem, P. . (2026). Spatiotemporal Crime Hotspot Detection in Chicago Using the Spatial-temporal Density-based Spatial Clustering of Applications with Noise (ST-DBSCAN) Clustering Algorithm. The Scientific Journal of Cihan University– Sulaimaniya, 10(1), 120-138. https://doi.org/10.25098/10.1.36

Issue

Section

Articles