Abstract

The rapid growth of digital technologies has led to a significant increase in crime and cybercrime incidents, necessitating the development of accurate and reliable predictive models to support proactive law enforcement and policy planning. Traditional machine learning approaches often rely on single classifiers, which suffer from limited generalization capability and higher prediction error when dealing with complex and heterogeneous crime data. To address these limitations, this work proposes a stacked ensemble learning framework for zone-wise crime and cybercrime risk prediction, integrating multiple machine learning algorithms with a meta-learning strategy. The proposed methodology employs heterogeneous base classifiers, including Decision Tree, Naïve Bayes, Random Forest, and Support Vector Machine, whose individual predictions are combined using a Support Vector Machine-based meta-classifier through stacked generalization. A rigorous mathematical formulation is presented to model data normalization, base learner predictions, meta-feature construction, and ensemble optimization. Additionally, spatial risk modeling and clustering techniques are incorporated to identify high-risk zones and generate actionable crime vulnerability insights. Experimental evaluation demonstrates that the proposed stacked ensemble framework significantly outperforms individual classifiers in terms of accuracy, precision, recall, and error reduction metrics such as MAE and RMSE. The results confirm the effectiveness of ensemble stacking in capturing complex crime patterns and improving predictive reliability. The proposed model offers a scalable and robust solution for crime risk forecasting and can be effectively utilized by law enforcement agencies for early warning systems, targeted interventions, and data-driven urban safety planning.

References

• Abdelghafour, E. B., Mohamed, C., Aknin, N., & Bouzidi, A. (2024). Enhancing Credit Card Fraud Detection Using a Stacking Model Approach and Hyperparameter Optimization. International Journal of Advanced Computer Science and Applications, 15(10). https://doi.org/10.14569/ijacsa.2024.01510110
• Airlangga, G. (2024). A Hybrid Ensemble Approach for Enhanced Fraud Detection: Leveraging Stacking Classifiers to Improve Accuracy in Financial Transaction. Journal of Computer System and Informatics (JoSYC), 5(4), 1118. https://doi.org/10.47065/josyc.v5i4.5840
• Alahmadi, A. (2024). Screening Cyberattacks and Fraud via Heterogeneous Layering. International Journal of Advanced Computer Science and Applications, 15(3). https://doi.org/10.14569/ijacsa.2024.01503135
• Alhashmi, A. A., Alashjaee, A. M., Darem, A. A., Alanazi, A. F., & Effghi, R. (2023). An Ensemble-based Fraud Detection Model for Financial Transaction Cyber Threat Classification and Countermeasures. Engineering Technology & Applied Science Research, 13(6), 12433. https://doi.org/10.48084/etasr.6401
• Alserhani, F., & Aljared, A. (2023). Evaluating Ensemble Learning Mechanisms for Predicting Advanced Cyber Attacks. Applied Sciences, 13(24), 13310. https://doi.org/10.3390/app132413310
• Anis, G., Aboutabl, A. E., & Galal, A. (2023). MACHINE LEARNING FOR DETECTING CYBERCRIME IN THE BANKING SECTOR. Journal of Southwest Jiaotong University, 58(5). https://doi.org/10.35741/issn.0258-2724.58.5.60
• Bodyanskiy, Y., Lipianina-Honcharenko, Kh. V., & Sachenko, A. (2024). ENSEMBLE OF ADAPTIVE PREDICTORS FOR MULTIVARIATE NONSTATIONARY SEQUENCES AND ITS ONLINE LEARNING. Radio Electronics Computer Science Control, 4, 91. https://doi.org/10.15588/1607-3274-2023-4-9
• Chelloug, S. A. (2024). A Robust Approach for Multi Classification-Based Intrusion Detection through Stacking Deep Learning Models. Computers, Materials & Continua/Computers, Materials & Continua (Print), 79(3), 4845. https://doi.org/10.32604/cmc.2024.051539
• Divyasri, S. R., Saranya, R., & Kathiravan, P. (2023). Comprehensive analysis of Classical Machine Learning models and Ensemble methods for predicting Crime in urban society. Research Square (Research Square). https://doi.org/10.21203/rs.3.rs-2550707/v2
• Jiang, T., Li, J., Haq, A. U., Saboor, A., & Ali, A. (2021). A Novel Stacking Approach for Accurate Detection of Fake News. IEEE Access, 9, 22626. https://doi.org/10.1109/access.2021.3056079
• Kaddi, S. S., & Patil, M. M. (2023). Ensemble learning based health care claim fraud detection in an imbalance data environment. Indonesian Journal of Electrical Engineering and Computer Science, 32(3), 1686. https://doi.org/10.11591/ijeecs.v32.i3.pp1686-1694
• Karthik, P., Jayanth, P., Nayak, K. T., & Kumar, K. A. (2024). Crime Prediction Using Machine Learning and Deep Learning. International Journal of Scientific Research in Science Engineering and Technology, 11(3), 8. https://doi.org/10.32628/ijsrset241134
• Khekare, G., Sunda, S., & Bothra, Y. (2025). A Comprehensive Performance Comparison of Traditional and Ensemble Machine Learning Models for Online Fraud Detection. https://doi.org/10.48550/ARXIV.2509.17176
• Lamari, Y., Freškura, B., Abdessamad, A., Eichberg, S., & Bonviller, S. de. (2020). Predicting Spatial Crime Occurrences through an Efficient Ensemble-Learning Model. ISPRS International Journal of Geo-Information, 9(11), 645. https://doi.org/10.3390/ijgi9110645
• Li, J. (2022). E-Commerce Fraud Detection Model by Computer Artificial Intelligence Data Mining. Computational Intelligence and Neuroscience, 2022, 1. https://doi.org/10.1155/2022/8783783
• Monika, E., & Kumar, T. R. (2024). A Unified Framework for Crime Prediction Leveraging Contextual and Interaction-Based Feature Engineering. Research Square (Research Square). https://doi.org/10.21203/rs.3.rs-5215161/v1
• Ozkan-Okay, M., Akin, E., Aslan, Ö., Koşunalp, S., Iliev, T., Stoyanov, I., & Beloev, I. (2024). A Comprehensive Survey: Evaluating the Efficiency of Artificial Intelligence and Machine Learning Techniques on Cyber Security Solutions. IEEE Access, 12, 12229. https://doi.org/10.1109/access.2024.3355547
• Pandey, H., Goyal, R., Virmani, D., & Gupta, C. (2021). Ensem_SLDR: Classification of Cybercrime using Ensemble Learning Technique. International Journal of Computer Network and Information Security, 14(1), 81. https://doi.org/10.5815/ijcnis.2022.01.07
• Rani, S., & Kumar, S. (2025). Enhancing intrusion detection accuracy with feature fusion and stacked ensemble approach: a dual-level learning framework. International Journal of Information Technology, 17(8), 5053. https://doi.org/10.1007/s41870-025-02711-w
• Raymond, L. L. (2024). A HETEROGENEOUS ENSEMBLE MODEL FOR FORECASTING STOCK MARKET MONTHLY DIRECTION. International Journal of Advanced Research in Computer Science, 15(5), 38. https://doi.org/10.26483/ijarcs.v15i5.7122
• Shi, J., Lin, S., Ding, N., Song, J., & Zhai, Y. (2025). Cyber Finance Fraud Recognition Method Based on Ensemble Machine Learning. Computational Economics. https://doi.org/10.1007/s10614-025-11091-z
• Shu, K., Sliva, A., Wang, S., Tang, J., & Liu, H. (2017). Fake News Detection on Social Media: A Data Mining Perspective. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1708.01967
• SINDHU, S. (2025). Stacking Ensemble Learning : Combining XGBoost, LightGBM, CatBoost, and AdaBoost with Random Forest Meta Model. https://doi.org/10.21203/rs.3.rs-7944070/v1
• Singh, S. S. K., Menon, V. K. N., Sajidha, S. A., Nisha, V. M., A, S. A., Nivedita, M., & Mairaj, A. (2023). Meta Learning for Enhanced Web Security Against Malicious URLs. Research Square (Research Square). https://doi.org/10.21203/rs.3.rs-3626868/v1
• Waghchaware, S., & Joshi, R. D. (2024). Machine learning and deep learning models for human activity recognition in security and surveillance: a review [Review of Machine learning and deep learning models for human activity recognition in security and surveillance: a review]. Knowledge and Information Systems, 66(8), 4405. Springer Science+Business Media. https://doi.org/10.1007/s10115-024-02122-6
• Wang, W., Harrou, F., Sidi-Mohammed, S., & Sun, Y. (2025). Improving cyber-attack detection in Internet of Medical Things using ensemble deep learning methods. Cluster Computing, 28(14). https://doi.org/10.1007/s10586-025-05660-y
• Wang, Z., Chen, X., Wu, Y., Jiang, L., Lin, S., & Qiu, G. (2025). A robust and interpretable ensemble machine learning model for predicting healthcare insurance fraud. Scientific Reports, 15(1), 218. https://doi.org/10.1038/s41598-024-82062-x
• Zhang, Z., Zhou, X., Zhang, X., Wang, L., & Wang, P. (2018). A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection. Security and Communication Networks, 2018, 1. https://doi.org/10.1155/2018/5680264
• Zhu, S., Wu, H., Ngai, E. W. T., Ren, J., He, D., Ma, T., & Li, Y. (2024). A Financial Fraud Prediction Framework Based on Stacking Ensemble Learning. Systems, 12(12), 588. https://doi.org/10.3390/systems12120588
• Zioviris, G., Kolomvatsos, K., & Stamoulis, G. (2024). An intelligent sequential fraud detection model based on deep learning. The Journal of Supercomputing, 80(10), 14824. https://doi.org/10.1007/s11227-024-06030-y
• S. S. Kshatri, D. Singh, B. Narain, S. Bhatia, M. T. Quasim and G. R. Sinha, "An Empirical Analysis of Machine Learning Algorithms for Crime Prediction Using Stacked Generalization: An Ensemble Approach," in IEEE Access, vol. 9, pp. 67488-67500, 2021, doi: 10.1109/ACCESS.2021.3075140.
• Angbera, A., Chan, H.Y. An adaptive XGBoost-based optimized sliding window for concept drift handling in non-stationary spatiotemporal data streams classifications. J Supercomput 80, 7781–7811 (2024). https://doi.org/10.1007/s11227-023-05729-8.