Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal SMARTICS Journal
Rahmi, Sutria
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Prediksi Tingkat Keamanan Terhadap Pencurian Menggunakan Naive Bayes di Wilayah Sektor Kepolisian Merapi Barat Rahmi, Sutria; Permatasari, Indah; Purnamasari, Evi
SMARTICS Journal Vol 12 No 1 (2026): Journal SMARTICS (April 2026)
Publisher : Universitas PGRI Kanjuruhan Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21067/smartics.v12i1.13919

Abstract

Theft remains one of the most prevalent forms of criminal activity in the jurisdiction of the West Merapi Police Sector, significantly impacting public safety and community security. Historically, the handling and securing of this region has been reactive in nature, lacking a predictive system capable of estimating theft risks preventively. This study aims to develop a predictive model for regional security levels related to theft cases using a machine learning approach. The data utilized in this research comprises secondary data obtained from 459 theft case reports documented by the West Merapi Police Sector from 2021 to 2024. Ten relevant variables were selected as features, while three security level categories (Low, Medium, and High) served as target classes. Data preprocessing included data cleaning, variable transformation, and label encoding. The Naive Bayes algorithm was employed with a 70% training data and 30% testing data split. The results demonstrated that the Naive Bayes method achieved an accuracy of 76.09% in predicting regional security levels. The model exhibited optimal performance for the High security level class, while the Low class showed lower performance due to imbalanced data distribution. This research demonstrates that police case report data can be effectively utilized to support data-driven risk analysis and has the potential to serve as a decision-making tool for preventive measures by law enforcement agencies.
Co-Authors Indah Permatasari Purnamasari, Evi