Crime Analytics Pro: An Integrated Machine Learning and Geospatial Intelligence Platform for Predictive Crime Forecasting and Hotspot Detection

Crime Analytics Pro demonstrates the effective integration of ML, geospatial intelligence, and time series forecasting in a scalable, interpretable, and user-accessible crime prediction plat-form. Key contributions include: (1) supervised ML achieving 87.4% prediction accuracy; (2) DBSCAN-based hotspot detec-tion with 93.7% precision; (3) time series forecasting up to 12 months with R2≥0.85; (4) automated preprocessing pipelines handling datasets exceeding 900,000 records; and (5) Streamlit dashboards rated 4.7 / 5 by non-technical users. All defined suc-cess criteria are met. The platform enables law enforcement to shift from reactive policing to evidence-based proactive crime prevention, contributing meaningfully to the goal of data-driven urban governance [11].

[1]     A. Al-Shehari, R. Alsini, H. Al-Qudah, N. L. Fitriyani, M. Ghulam, and M. Syafrudin, “CHART: Intelligent crime hotspot detection and real-time tracking using machine learning,” Computers, Materials & Continua, vol. 81, no. 3, pp. 4287–4308, 2024. [2]     M. Liu, L. Wu, Y. Yang, and S. Li, “Research on a crime spatiotemporal prediction method integrating informer and ST-GCN: A case study of four crime types in chicago,” Big Data and Cognitive Computing, vol. 8, no. 7, p. 179, 2024. V. Mandalapu, L. Elluri, P. Vyas, and N. Roy, “Crime prediction using machine learning and deep learning: A systematic review and future directions,” IEEE Access, vol. 11, pp. 60470–60489, 2023. Y. Chen, J. Li, X. Wang, and J. Zhang, “A systematic review of multi-scale spatio-temporal crime prediction methods,” ISPRS International Journal of Geo-Information, vol. 12, no. 6, p. 209, 2023. [5]     M. Yasir, M. Habib, W. Ahmad, and M. Y. Khan, “Em-pirical analysis for crime prediction and forecasting using machine learning and deep learning techniques,” IEEE Ac-cess, vol. 11, pp. 43468–43485, 2023. [6]     J. Bernardino-Angulo, J. P. Escobedo-Cabello, E. Báez-García, and R. Tejeida-Padilla, “Deep learning for crime forecasting of multiple regions, considering spatial–temporal correlations between regions,” Computers, vol. 13, no. 6, p. 144, 2024. [7]     X. Wang, Y. Chen, Y. Liu, and H. Xiong, “Interpretable ma-chine learning models for crime prediction,” Information Sciences, vol. 634, pp. 141–158, 2023. [8]    S. Ahmad, I. Gondal, J. Kamruzzaman, and W. Mahmood, “Deep learning based crime prediction models: Exper-iments and analysis.” arXiv preprint arXiv:2407.19324, 2024. [9]    Z. Wang, Y. Li, X. Su, G. Gao, P. Wang, and Y. Liang, “Uncertainty-aware crime prediction with spatial temporal multivariate graph neural networks,” in Proc. 33rd ACM Int. Conf. Information and Knowledge Management (CIKM 2024), 2024. arXiv:2408.04193. [10]     X. Li, J. Li, J. Li, and Y. Li, “Research on crime risk prediction model based on machine learning,” in Proc. 13th Int. Conf. Computing and Pattern Recognition (ICCPR 2024), pp. 325–330, 2024.