[1]LI Zehui,SUI Jinguang,CHEN Peng,et al.Multitype crime prediction model integrating spatiotemporal interaction features and spatiotemporal correlation of crimes[J].CAAI Transactions on Intelligent Systems,2025,20(6):1339-1354.[doi:10.11992/tis.202502022]
Copy

Multitype crime prediction model integrating spatiotemporal interaction features and spatiotemporal correlation of crimes

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 6 Page number: 1339-1354 Column: 学术论文—机器学习 Public date: 2025-11-05
Title:
Multitype crime prediction model integrating spatiotemporal interaction features and spatiotemporal correlation of crimes
Author(s):
LI Zehui1;  SUI Jinguang2;  CHEN Peng1;  SHAN Miaoxuan1;  CHEN Jiaqi1
1. School of Information Network Security, People’s Public Security University of China, Beijing 102600, China;
2. School of Criminology, People’s Public Security University of China, Beijing 102600, China
Keywords:
crime spatiotemporal prediction; domain adaptation techniques; crime type correlation; graph convolutional neural network; spatiotemporal data mining; deep learning; attention mechanisms; data fusion
CLC:
TP183
DOI:
10.11992/tis.202502022
Abstract:
To address the high deployment costs of single-crime prediction models in policing practice, a multitype crime prediction model integrating spatiotemporal interaction features and spatiotemporal correlation of crimes (MCPM) was constructed. The model’s fundamental functionality encompasses two primary components: spatiotemporal interaction feature extraction and multitype joint learning. The spatiotemporal interaction feature extraction component is designed to capture the key characteristics of environmental features data related to different types of crime, while the multitype joint learning component integrates the spatiotemporal correlations among different types of crime, facilitating the joint optimization of spatiotemporal prediction for multiple crime types. A series of experiments have been conducted on data concerning robbery and burglary crime from Chicago and New York. The following conclusions were reached: The MCPM model demonstrates superior performance in terms of prediction accuracy, with a minimum prediction root mean square error of 0.365 for robbery and 0.288 for burglar and mean absolute error reaches a minimum of 0.277 and 0.226, respectively, indicating a significant margin of improvement over baseline models, with a maximum difference of 31.1% and 36.6%, respectively. Ablation experiments reveal that environmental features data variables contribute the most to the model’s predictions, followed by spatiotemporal correlations between different types of crime. The MCPM model effectively captures the differentiated impact of environmental features data on various crime types, enhancing model performance through the integration of spatiotemporal correlations among crimes.
References:
[1] 刘恩博, 谌恺祺, 石岩, 等. 数据不确定性下的犯罪事件热点探测方法[J]. 武汉大学学报(信息科学版), 2024, 49(12): 2342-2354.
LIU Enbo, CHEN Kaiqi, SHI Yan, et al. Hot spot detection method of criminal events under data uncertainty[J]. Geomatics and Information Science of Wuhan University, 2024, 49(12): 2342-2354.
[2] 卢建平, 王昕宇. “党的十八大”以来犯罪形势的宏观、中观与微观考察: 基于司法统计数据的分析[J]. 犯罪研究, 2023(1): 32-51
LU Jianping, WANG Xinyu. A macro, meso and micro observation of the crime situation since the 18th National Congress of the CPC: an analysis based on criminal statistics[J]. Chinese criminology review, 2023(1): 32-51
[3] ZHAO Xiangyu, FAN Wenqi, LIU Hui, et al. Multi-type urban crime prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(4): 4388-4396.
[4] 阎耀军, 张明. 犯罪预测时空定位信息管理系统的构建[J]. 中国人民公安大学学报(社会科学版), 2013, 29(4): 73-80.
YAN Yaojun, ZHANG Ming. Construction of information management system for spatial and temporal location of crime prediction[J]. Journal of People’s Public Security University of China (social sciences edition), 2013, 29(4): 73-80.
[5] 新浪科技.美警方测试犯罪预测软件可大幅降低犯罪率[EB/OL].（2012-07-17） [2025-05-14]. http://tech.sina.com.cn/d/2012-07-17/08017395390.shtml.
[6] 姜春娇, 李慧. 基于犯罪预测智能平台的警务建设研究[J]. 公安研究, 2017(4): 34-40.
JIANG Chunjiao, LI Hui. Research on police construction based on intelligent platform of crime prediction[J]. Policing studies, 2017(4): 34-40.
[7] 赵锃泽, 刘大千, 郑滋椀, 等. 警务检查活动对盗窃犯罪的空间影响研究: 以浙江海宁市为例[J]. 地理科学进展, 2024, 43(11): 2298-2311.
ZHAO Zengze, LIU Daqian, ZHENG Ziwan, et al. Spatial influence of police inspection activities on theft crimes: a case study in Haining City, Zhejiang[J]. Progress in geography, 2024, 43(11): 2298-2311.
[8] 徐冲, 柳林, 周素红. 基于临近相似性考虑的犯罪热点密度图预测准确性比较: 以DP半岛街头抢劫犯罪为例[J]. 地理科学, 2016, 36(1): 55-62.
XU Chong, LIU Lin, ZHOU Suhong. The comparison of predictive accuracy of crime hotspot density maps with the consideration of the near similarity: a case study of robberies at DP peninsula[J]. Scientia geographica sinica, 2016, 36(1): 55-62.
[9] 柳林, 刘文娟, 廖薇薇, 等. 基于随机森林和时空核密度方法的不同周期犯罪热点预测对比[J]. 地理科学进展, 2018, 37(6): 761-771.
LIU Lin, LIU Wenjuan, LIAO Weiwei, et al. Comparison of random forest algorithm and space-time kernel density mapping for crime hotspot prediction[J]. Progress in geography, 2018, 37(6): 761-771.
[10] HUANG Chao, ZHANG Junbo, ZHENG Yu, et al. DeepCrime: attentive hierarchical recurrent networks for crime prediction[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Torino: ACM, 2018: 1423-1432.
[11] HUANG Chao, ZHANG Chuxu, ZHAO Jiashu, et al. MiST: a multiview and multimodal spatial-temporal learning framework for citywide abnormal event forecasting[C]//The World Wide Web Conference. San Francisco: ACM, 2019: 717-728.
[12] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//International Conference on Learning Representations. Vancouver: ICLR, 2018: 1-12.
[13] YU Bing, YIN Haoteng, ZHU Zhanxing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm: International Joint Conferences on Artificial Intelligence Organization, 2018: 3634-3640.
[14] ZHAO Liupeng. A study on the application of data mining-based crime prediction models in criminal justice[J]. Journal of combinatorial mathematics and combinatorial computing, 2024, 123(1): 559-575.
[15] 林逸航, 郑坤, 夏书豪, 等. 融合区域空间相似性特征与事件时空特征的犯罪预测模型[J/OL]. 武汉大学学报(信息科学版). https://doi.org/10.13203/j.whugis20230395.
LIN Yihang, ZHENG Kun, XIA Shuhao, et al. A crime prediction model incorporating regional spatial similarity characteristics and spatio-temporal characteristics of events[J/OL]. Geomatics and Information Science of Wuhan University. https://doi.org/10.13203/j.whugis20230395.
[16] ZHAO Xiangyu, TANG Jiliang. Modeling temporal-spatial correlations for crime prediction[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. Singapore: ACM, 2017: 497-506.
[17] SHAN Miaoxuan, YE Chunlin, CHEN Peng, et al. Ada-GCNLSTM: an adaptive urban crime spatiotemporal prediction model[J]. Journal of safety science and resilience, 2025, 6(2): 226-236.
[18] 石拓, 张齐, 石磊. 多尺度视角特征动态融合的盗窃犯罪预测模型[J]. 智能系统学报, 2022, 17(6): 1104-1112.
SHI Tuo, ZHANG Qi, SHI Lei. Prediction model of theft crime based on the dynamic fusion of multiscale perspective characteristics[J]. CAAI transactions on intelligent systems, 2022, 17(6): 1104-1112.
[19] 柳林, 纪佳楷, 宋广文, 等. 基于犯罪空间分异和建成环境的公共场所侵财犯罪热点预测[J]. 地球信息科学学报, 2019, 21(11): 1655-1668.
LIU Lin, JI Jiakai, SONG Guangwen, et al. Hotspot prediction of public property crime based on spatial differentiation of crime and built environment[J]. Journal of geo-information science, 2019, 21(11): 1655-1668.
[20] 贺日兴, 唐宗棣, 姜超, 等. 顾及道路权重的图卷积犯罪时空预测模型[J]. 地球信息科学学报, 2023, 25(10): 1986-1999.
HE Rixing, TANG Zongdi, JIANG Chao, et al. A graph convolution-based spatio-temporal crime prediction model considering road weights[J]. Journal of geo-information science, 2023, 25(10): 1986-1999.
[21] LI Zhe, ZHANG Xinyue, XU Fang, et al. A multi-scale video surveillance based information aggregation model for crime prediction[J]. Alexandria engineering journal, 2023, 73: 695-707.
[22] 李卫红, 闻磊, 陈业滨. 改进的GA-BP神经网络模型在财产犯罪预测中的应用[J]. 武汉大学学报(信息科学版), 2017, 42(8): 1110-1116,1171.
LI Weihong, WEN Lei, CHEN Yebin. Property crime forecast based on improved GA-BP neural network model[J]. Geomatics and information science of Wuhan University, 2017, 42(8): 1110-1116,1171.
[23] DAVIES T P, BISHOP S R. Modelling patterns of burglary on street networks[J]. Crime science, 2013, 2(1): 10.
[24] WHEELER A P, REUTER S. Redrawing hot spots of crime in Dallas, Texas[J]. Police quarterly, 2021, 24(2): 159-184.
[25] WHEELER A P, STEENBEEK W. Mapping the risk terrain for crime using machine learning[J]. Journal of quantitative criminology, 2021, 37(2): 445-480.
[26] YU Hongjie, LIU Lin, YANG Bo, et al. Crime prediction with historical crime and movement data of potential offenders using a spatio-temporal cokriging method[J]. ISPRS international journal of geo-information, 2020, 9(12): 732.
[27] HAN Xinge, HU Xiaofeng, WU Huanggang, et al. Risk prediction of theft crimes in urban communities: an integrated model of LSTM and ST-GCN[J]. IEEE access, 2020, 8: 217222-217230.
[28] ZHANG Tianyi, RAN Yibing, WEI Dong. Application of grid management in spatio-temporal prediction of crime[C]//2021 33rd Chinese Control and Decision Conference. Kunming: IEEE, 2021: 2745-2749.
[29] 徐冲, 柳林, 周素红, 等. 微观空间因素对街头抢劫影响的空间异质性: 以DP半岛为例[J]. 地理研究, 2017, 36(12): 2492-2504.
XU Chong, LIU Lin, ZHOU Suhong, et al. Spatial heterogeneity of micro-spatial factors’ effects on street robberies: a case study of DP peninsula[J]. Geographical research, 2017, 36(12): 2492-2504.
[30] FENG Jiajia, LIANG Yuebing, HAO Qi, et al. Comparing effectiveness of point of interest data and land use data in theft crime modelling: a case study in Beijing[J]. Land use policy, 2024, 147: 107357.
[31] LEE D W, LEE D S. Analysis of influential factors of violent crimes and building a spatial cluster in south Korea[J]. Applied spatial analysis and policy, 2020, 13(3): 759-776.
[32] SUMMERS L, JOHNSON S D. Does the configuration of the street network influence where outdoor serious violence takes place? using space syntax to test crime pattern theory[J]. Journal of quantitative criminology, 2017, 33(2): 397-420.
[33] RISTEA A, BONI M I, RESCH B, et al. Spatial crime distribution and prediction for sporting events using social media[J]. International journal of geographical information science, 2020, 34(9): 1708-1739.
[34] 沈兵. 城市犯罪风险时空分布预测方法研究[D]. 北京: 中国人民公安大学, 2022.
SHEN Bing. Study on the prediction method of urban crime risk spatial and temporal distribution[D]. Beijing: Chinese People’s Public Security University, 2022.
[35] SAMPSON R J, GROVES W B. Community structure and crime: testing social-disorganization theory[J]. American journal of sociology, 1989, 94(4): 774-802.
[36] 柳林, 杜方叶, 宋广文, 等. 犯罪共生空间的类型识别及其特征分析[J]. 地理科学, 2018, 38(8): 1199-1209.
LIU Lin, DU Fangye, SONG Guangwen, et al. Detecting and characterizing symbiotic clusters of crime[J]. Scientia geographica sinica, 2018, 38(8): 1199-1209.
[37] 王文汐, 霍宏涛, 蒋晨琛. 毒品犯罪与次生犯罪共生关系: 以华北沿海T市为例[J]. 科学技术与工程, 2023, 23(33): 14486-14496.
WANG Wenxi, HUO Hongtao, JIANG Chenchen. Exploring colocalization relationship between drug-related crimes and secondary crimes: take T city on the coast of North China as an example[J]. Science technology and engineering, 2023, 23(33): 14486-14496.
[38] CELIK M. Partial spatio-temporal co-occurrence pattern mining[J]. Knowledge and information systems, 2015, 44(1): 27-49.
[39] LI Ling, CHENG Jianquan, BANNISTER J, et al. Geographically and temporally weighted co-location quotient: an analysis of spatiotemporal crime patterns in greater Manchester[J]. International journal of geographical information science, 2022, 36(5): 918-942.
[40] DE OLIVEIRA V H, DE MEDEIROS C N, CARVALHO J R. Violence and local development in Fortaleza, Brazil: a spatial regression analysis[J]. Applied spatial analysis and policy, 2019, 12(1): 147-166.
[41] ZHANG Yang, CHENG Tao. Graph deep learning model for network-based predictive hotspot mapping of sparse spatio-temporal events[J]. Computers, environment and urban systems, 2020, 79: 101403.
[42] ZHAO Ling, SONG Yujiao, ZHANG Chao, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE transactions on intelligent transportation systems, 2020, 21(9): 3848-3858.
[43] FARRELL G, PEASE K. Once bitten, twice bitten: Repeat victimisation and its implications for crime prevention[M]. London: Home Office Police Research Group, 1993: 46-52.
[44] SCH?LKOPF B, PLATT J, HOFMANN T. Analysis of representations for domain adaptation[C]//Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference. Vancouver: MIT Press, 2007: 137-144.
[45] City of Chicago Open Data Portal[DB/OL]. (2024-07-30) [2025-01-04]. https://data.cityofchicago.org.
[46] NYC Open Data[DB/OL]. (2024-12-01) [2025-01-04]. https://opendata.cityofnewyork.us.
[47] ECK J E, WEISBURD D. Crime places in crime theory[J]. Social science electronic publishing, 1995, 4: 1-33.
[48] 贺日兴, 陆宇梅, 姜超, 等. 近10年来犯罪时空预测国内外研究与实践进展[J]. 地球信息科学学报, 2023, 25(4): 866-882.
HE Rixing, LU Yumei, JIANG Chao, et al. Progress in research and practice of spatial-temporal crime prediction over the past decade[J]. Journal of geo-information science, 2023, 25(4): 866-882.
[49] 顾海硕, 陈鹏, 李慧波. 犯罪时空预测方法研究综述与展望[J]. 地球信息科学学报, 2021, 23(1): 43-57.
GU Haishuo, CHEN Peng, LI Huibo. Overview and prospect for spatial-temporal prediction of crime[J]. Journal of geo-information science, 2021, 23(1): 43-57.
[50] CHEN Tianqi, HE Tong, BENESTY M, et al. Xgboost: extreme gradient boosting[C]//Processdings of 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Franciso:Association for Gomputing Machinery, 2016: 785-799.
[51] ALVES L G A, RIBEIRO H V, RODRIGUES F A. Crime prediction through urban metrics and statistical learning[J]. Physica A: statistical mechanics and its applications, 2018, 505: 435-443.
[52] SHI Xingjian, CHEN Zhourong, WANG Hao, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems 28 (NIPS 2015). Montreal: MIT Press, 2015: 802-810.
[53] LI Yaguang, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[EB/OL]. (2017-07-06)[2025-01-24]. https://arXiv.org/abs/1707.01926.
[54] WU Zonghan, PAN Shirui, LONG Guodong, et al. Graph wavenet for deep spatial-temporal graph modeling[EB/OL]. (2019-06-01)[2025-01-24]. https://arxiv.org/abs/1906.00121.
[55] RAYHAN Y, HASHEM T. AIST: an interpretable attention-based deep learning model for crime prediction[J]. ACM transactions on spatial algorithms and systems, 2023, 9(2): 1-31.
[56] ZHANG Yan, ZHAO Jihong, REN Ling, et al. Space–time clustering of crime events and neighborhood characteristics in Houston[J]. Criminal justice review, 2015, 40(3): 340-360.
[57] HABERMAN C P, RATCLIFFE J H. The predictive policing challenges of near repeat armed street robberies[J]. Policing, 2012, 6(2): 151-166.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems