Crime Data Analysis in Police Personnel with Machine Learning
Journals Fringe Multi-Engineering Proceedings · 2025
DOI: 10.69996/fmep.2025026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journals Fringe Multi-Engineering Proceedings, 2025.
Abstract (Originalsprache)
The increasing complexity and frequency of criminal activities demand intelligent solutions to support law enforcement agencies in maintaining public safety. This research presents a comprehensive crime data analysis framework aimed at enhancing the efficiency of police personnel deployment through machine learning techniques. By utilizing historical crime datasets, the study performs extensive data preprocessing including handling missing values, normalization, and feature categorization to uncover patterns and trends in criminal incidents. The analysis focuses on identifying victim demographics, weapon usage, crime timings, and high-risk areas through visualizations and statistical summaries. Various machine learning algorithms such as K-Nearest Neighbors (KNN), Logistic Regression, CART, and Random Forest are employed to classify and predict crime occurrences. The performance of these models is compared using metrics like accuracy, precision, and recall. The results demonstrate that CART and Random Forest outperform other models, making them suitable for crime prediction tasks. This datadriven approach empowers police departments with actionable insights for proactive intervention, smarter personnel allocation, and strategic planning to reduce crime rates and improve community security.
Zitieren
APA
(2025). Crime Data Analysis in Police Personnel with Machine Learning. Journals Fringe Multi-Engineering Proceedings. https://doi.org/10.69996/fmep.2025026
Vancouver
Crime Data Analysis in Police Personnel with Machine Learning. Journals Fringe Multi-Engineering Proceedings. 2025. doi:10.69996/fmep.2025026
BibTeX
@article{euvimed2025,
title = {Crime Data Analysis in Police Personnel with Machine Learning},
journal = {Journals Fringe Multi-Engineering Proceedings},
year = {2025},
doi = {10.69996/fmep.2025026}
}
EUVIMED