Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65620
Volume:
10 |
6 |
Jun 2026
Pages:
1-2
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.
Department of Computer Application
Nehru Institute of Information Technology and Management
Department of Computer Application
Nehru Institute of Information Technology and Management
Rising crime rates strain limited patrol resources, and traditional record-keeping systems remain descriptive rather than predictive. This paper presents CDAGSV, a modular Python analytics application combining crime-record ingestion, machine-learning hotspot and category prediction, and interactive geo-spatial visualization. Built on eight incident attributes (location, category, time, day, weapon use, victim demographics, arrest status, beat ID), a Random Forest classifier reaches 94.1% accuracy (F1 = 0.93) for crime-category prediction, a DBSCAN module detects statistically significant hotspots, and a Prophet model forecasts 7-day crime-volume trends per zone. A Flask dashboard renders Folium/Plotly choropleths, heatmaps, trend charts, and patrol-priority reports. Hotspot-informed allocation cuts response-zone mismatch by 27.6% versus static beats.
KEYWORDS
CDAGSV integrates structured crime analytics, Random Forest classification (94.1% accuracy), DBSCAN hotspot detection (89.4% corridor overlap), and Prophet forecasting (13.7% MAPE) into one production-ready decision-support tool, reducing response-zone mismatch by 27.6% over static beats. It contributes a documented analytics framework, a realistic structured dataset, and an educational codebase spanning classification, clustering, and geo-visualization.
[1] Chainey, Tompson & Uhlig, Security Journal 21(1-2), 4-28, 2008. [2] Ratcliffe, Police Practice and Research 5(1), 5-23, 2004. [3] Kim, Lee & Han, Proc. IEEE Big Data, 1452-1458, 2018. [4] Lin, Yen & Yu, ISPRS Int. J. Geo-Info. 7(8), 298, 2018. [5] Wang et al., Pattern Analysis and Applications, 2016. [6] Ester, Kriegel, Sander & Xu, Proc. KDD, 226-231, 1996. [7] Kuo, Liu & Eck, Applied Geography 86, 162-172, 2017. [8] Wang & Brown, Proc. IEEE ISI, 2019. [9] Taylor & Letham, The American Statistician 72(1), 37-45, 2018.
Publication Date
6/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
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...