Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68750
Volume:
10 |
11 |
Nov 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Artificial intelligence and data science
Shri Swami Samarth Institute of Management and Technology

Artificial intelligence and data science
Shri Swami Samarth Institute of Management and Technology

Artificial intelligence and data science
Shri Swami Samarth Institute of Management and Technology
Modern law enforcement agencies aggregate vast volumes of unstructured and semi-structured crime records, First Information Reports (FIRs), and telecommunication metadata. Traditional manual crime mapping and investigative heuristics fail to uncover complex, hidden relational links within syndicated criminal networks. To bridge this critical capability gap, this paper introduces an intelligent framework combining Graph Neural Networks (GNNs) and Deep Spatio-Temporal Predictive Analytics for automated criminal network mining and proactive hotspot forecasting. The system transforms static relational databases into dynamic graph structures to identify key criminal influencers via Centrality Mathematical Modeling while utilizing Spatio-Temporal Recurrent Neural Networks (ST-RNN) for predicting future criminal occurrences. Empirical evaluations on benchmarked law enforcement datasets demonstrate a 94.8% accuracy in key actor identification and a 42% operational latency reduction in investigative link analysis compared to traditional relational database querying methods.
KEYWORDS
This research introduced an AI-driven framework integrating Graph Neural Networks and spatio-temporal deep learning to automate criminal network mapping and predictive crime forecasting. Experimental results demonstrate high precision (95.4%) in identifying covert links and high-value criminal targets within law enforcement databases. Future research will focus on integrating privacy-preserving Federated Learning architectures to facilitate secure cross-border intelligence sharing without compromising sensitive citizen data.
1. J. Xu and H. Chen, "Criminal network analysis and visualization," Communications ofthe ACM, vol. 48, no. 6, pp. 100-107, 2005. 2. W. Hamilton, Z. Ying, and J. Leskovec, "Inductive representation learning on large graphs," in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 1024-1034. 3. T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," in ICLR, 2017. 4. A. Babakurbanov et al., "Predictive policing using spatio-temporal data analysis: A survey," IEEE Access, vol. 9, pp. 88120-88135, 2021 . 5. IEEE Standard for Information Technology Software Quality Assurance, IEEE Std 730-2014, 2014. 6. G. Wang, C. Zhang, and L. Yu, "Deep learning for crime prediction: A comprehensive review," ACMComputing Surveys, vol. 54, no. 5, pp. 1 - 35, 2022. 7. D. B. Skillicorn, "Knowledge Discovery for Counterterrorism and Law Enforcement," CRC Press, 2008. 8. V. E. Krebs, "Mapping networks of terrorist cells," Connections, vol.24, no. 3, pp. 43-52, 2002. 9. M. Perry, "Predictive policing: The role of crime forecasting in law enforcement operations," RAND Corporation Research Report, 2013. 10. X. Rong, "Node2vec: Scalable feature learning for networks," in ACM SIGKDD, 2016, pp. 855-864.
Publication Date
11/7/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...