Authors : Sundari Palanisamy; Malathi Arunachalam; Raniyaharini Rajendran

Volume/Issue : Volume 10 - 2025, Issue 10 - October

Google Scholar : https://tinyurl.com/4jkm2ce8

Scribd : https://tinyurl.com/6td2yvns

DOI : https://doi.org/10.38124/ijisrt/25oct186

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Law enforcement agencies rely on accurate crime prediction systems to study past and present crime trends in order to forecast and prevent future incidents. Among Deep Learning (DL) approaches, time series prediction using Long Short-Term Memory (LSTM) networks is popular because modeling long-term temporal dependencies and sequential patterns is necessary for crime data. However, LSTM struggles with large number of parameters due to three gates, difficulty in capturing very short-term dependencies and increased memory consumption, limits the prediction on real-time crime datasets. For spatial learning, Graph Convolutional Networks (GCNs) have been used to capture crime area based correlations and spatial dependencies in crime data. However, GCN often overfit to local graph structures, struggle to extract transferable features across diverse regions and exhibit reduced performance when spatial data is noisy or incomplete. To overcome such limitations a Graph Convolutional Network with Gated Recurrent Unit (GCN-GRU) is put forward in this paper to enhance crime prediction. In this model, GCN dynamically adapts the graph topology based on spatial data characteristics to extract relevant features across diverse spatial regions in the crime dataset. Also, this mechanism captures both local and global spatial dependencies improve resilient to noisy or incomplete data. By updating neighborhood relationships during training, GCN avoids dependence on fixed local structures reducing overfitting and improving spatial feature stability. GRU employs only two gates (reset and update) with fewer parameters enabling faster training and lower memory usage. Moreover, the reset gate enhances the handling of sudden and short-term variations in sequential crime data while preserving the ability to technique long-standing needs. In the temporal modeling module, GRU network captures the underlying relationships between sequential crime events and their temporal patterns. Along with this Cross-Entropy Loss function is employed to help the method to give greater probabilities to correct crime categories to improve classification accuracy and enhance decision confidence in crime prediction. Thus, GCN improves spatial feature mapping and GRU enhances temporal sequence learning in enhanced crime classification. Experimental results demonstrate that the proposed GCN-GRU outperforms existing baseline approaches in crime prediction.

Keywords : Crime Prediction, DL, LSTM, Cross Entropy Loss Function and Spatial Temporal Feature.

References :

1. A. Tamir, E. Watson, B. Willett, Q. Hasan, and J. S. Yuan, “Crime prediction and forecasting using machine learning algorithms,” Int. J. Comput. Sci. Inf. Technol., vol. 12, no. 2, pp. 26–33, 2021.
2. J. Alghamdi and T. Al-Dala’in, “Towards spatio-temporal crime events prediction,” Multimedia Tools Appl., vol. 83, no. 7, pp. 18721–18737, 2024.
3. Y. Hua, Z. Zhao, R. Li, X. Chen, Z. Liu, and H. Zhang, “Deep learning with long short-term memory for time series prediction,” IEEE Commun. Mag., vol. 57, no. 6, pp. 114–119, Jun. 2019.
4. Y. Du and N. Ding, “A systematic review of multi-scale spatio-temporal crime prediction methods,” ISPRS Int. J. Geo-Inf., vol. 12, no. 6, p. 209, 2023.
5. G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5929–5955, 2020.
6. P. Lara-Benítez, M. Carranza-García, and J. C. Riquelme, “An experimental review on deep learning architectures for time series forecasting,” Int. J. Neural Syst., vol. 31, no. 03, p. 2130001, 2021.
7. S. K. Mathivanan, H. Rajadurai, J. Cho, and S. V. Easwaramoorthy, “A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns,” Sci. Rep., vol. 14, no. 1, p. 31579, 2024.
8. G. Jin, Y. Liang, Y. Fang, Z. Shao, J. Huang, J. Zhang, and Y. Zheng, “Spatio-temporal graph neural networks for predictive learning in urban computing: A survey,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 10, pp. 5388–5408, Oct. 2023.
9. T. Zubair, S. K. Fatima, N. Ahmed, and A. Khan, “Crime hotspot prediction using deep graph convolutional networks,” arXiv preprint arXiv:2506.13116, 2025.
10. S. Bloemheuvel, J. van den Hoogen, and M. Atzmueller, “Graph construction on complex spatiotemporal data for enhancing graph neural network-based approaches,” Int. J. Data Sci. Anal., vol. 18, no. 2, pp. 157–174, 2024.
11. W. Liang, Y. Wang, H. Tao, and J. Cao, “Towards hour-level crime prediction: A neural attentive framework with spatial–temporal–categorical fusion,” Neurocomputing, vol. 486, pp. 286–297, 2022.
12. Q. Dong, Y. Li, Z. Zheng, X. Wang, and G. Li, “ST3DNetCrime: Improved ST-3DNet model for crime prediction at fine spatial temporal scales,” ISPRS Int. J. Geo-Inf., vol. 11, no. 10, p. 529, 2022.
13. N. Tasnim, I. T. Imam, and M. M. A. Hashem, “A novel multi-module approach to predict crime based on multivariate spatio-temporal data using attention and sequential fusion model,” IEEE Access, vol. 10, pp. 48009–48030, 2022.
14. Y. Rayhan and T. Hashem, “AIST: An interpretable attention-based deep learning model for crime prediction,” ACM Trans. Spatial Algorithms Syst., vol. 9, no. 2, pp. 1–31, 2023.
15. B. Zhou, H. Zhou, W. Wang, L. Chen, J. Ma, and Z. Zheng, “HDM-GNN: A heterogeneous dynamic multi-view graph neural network for crime prediction,” ACM Trans. Sensor Netw., 2024.
16. Z. Wang, X. Ma, H. Yang, W. Lyu, Y. Liu, P. Sun, and S. C. Guntuku, “Uncertainty-aware crime prediction with spatial temporal multivariate graph neural networks,” in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), Apr. 2025, pp. 1–5.
17. S. Wang, Y. Zhang, X. Piao, X. Lin, Y. Hu, and B. Yin, “MRAGNN: Refining urban spatio-temporal prediction of crime occurrence with multi-type crime correlation learning,” Expert Syst. Appl., vol. 265, p. 125940, 2025.
18. Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, “A comprehensive survey on graph neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 1, pp. 4–24, 2020, doi: 10.1109/TNNLS.2020.2978386.
19. Y. Wang, C. Chen, Y. Zhang, M. Zhang, and Y. Gao, “Deep temporal multi-graph convolutional network for crime prediction,” in Conceptual Modeling: Proc. 39th Int. Conf., ER 2020, Vienna, Austria, Nov. 3–6, 2020, pp. 678–689, doi: 10.1007/978-3-030-62522-1_39.
20. Y. Zhang, Y. Chen, J. Wang, and Z. Pan, “Unsupervised deep anomaly detection for multi-sensor time-series signals,” IEEE Trans. Knowl. Data Eng., 2021, doi: 10.1109/TKDE.2021.3102110.
21. “Crime in India dataset,” Kaggle, Available: https://www.kaggle.com/datasets/rajanand/crime-in-india. [Accessed: Aug. 28, 2025].