Analisis Tempat Lokasi Kejadian Rawan Kriminalitas Pencurian Motor diDaerah Kabupaten Musi Banyuasin dari Tahun 2021-2024 denganMenggunakan Metode Machine Learning Berfokus pada KlasifikasiPrediksi

Authors

  • Rossi Passarella Author
  • Adelia Wike Prayoga Author

Abstract

Pencurian sepeda motor merupakan salah satu
bentuk kejahatan yang sering terjadi di wilayah
berkembang seperti Kabupaten Musi Banyuasin.
Penelitian ini menerapkan algoritma Random Forest untuk
mengklasifikasikan wilayah berdasarkan tingkat risiko
kriminalitas ke dalam tiga kategori, Rawan, Cukup
Rawan, dan Aman. Model dibangun menggunakan data
riil kepolisian periode 2021–2024 yang terdiri dari 390
sampel dengan 13 fitur utama. Hasil penelitian
menunjukkan akurasi klasifikasi sebesar 85%, dengan
performa terbaik pada kelas Rawan, namun kelemahan
pada kelas Cukup Rawan akibat distribusi data yang tidak
seimbang. Penelitian ini memberikan kontribusi orisinal
dengan penerapan machine learning pada konteks spasial
lokal Kabupaten Musi Banyuasin yang belum banyak
diteliti. Hasil penelitian diharapkan dapat menjadi dasar
pengambilan keputusan pencegahan kejahatan yang
berbasis data.

References

[1] F. Liu, X. Zhao, and M. Wang, “Crime and Urban

Facilities: Spatial Differences and Planning Responses

in Changsha,” Sustainability (Switzerland), vol. 17,

no. 4, Feb. 2025, doi: 10.3390/su17041750.

[2] E. Halford and I. Gibson, “Using machine learning to

conduct crime linking of residential burglary,” Int J

Law Crime Justice, vol. 80, Mar. 2025, doi:

10.1016/j.ijlcj.2024.100716.

[3] M. Inzunza, “The significance of victim ideality in

interactions between crime victims and police

officers,” Int J Law Crime Justice, vol. 68, Mar. 2022,

doi: 10.1016/j.ijlcj.2021.100522.

[4] A. Alfardus and D. B. Rawat, “Machine Learning-

Based Anomaly Detection for Securing In-Vehicle

Networks,” Electronics (Switzerland), vol. 13, no. 10,

May 2024, doi: 10.3390/electronics13101962.

[5] X. Wang, R. Wang, S. Wei, and S. Xu, “Application

of Random Forest Method Based on Sensitivity

Parameter Analysis in Height Inversion in Changbai

Mountain Forest Area,” Forests, vol. 15, no. 7, Jul.

2024, doi: 10.3390/f15071161.

[6] F. Liu, X. Zhao, and M. Wang, “Crime and Urban

Facilities: Spatial Differences and Planning Responses

in Changsha,” Sustainability (Switzerland), vol. 17,

no. 4, Feb. 2025, doi: 10.3390/su17041750.

[7] A. Matsukawa and S. Tatsuki, “Crime prevention

through community empowerment: An empirical study

of social capital in Kyoto, Japan,” Int J Law Crime

Justice, vol. 54, pp. 89–101, Sep. 2018, doi:

10.1016/j.ijlcj.2018.03.007.

[8] Y. Mao, S. Dai, J. Ding, W. Zhu, C. Wang, and X. Ye,

“Space–time analysis of vehicle theft patterns in

Shanghai, China,” Canadian Historical Review, vol. 7,

no. 9, Sep. 2018, doi: 10.3390/ijgi7090357.

[9] A. Alsubayhin, M. Ramzan, and B. Alzahrani, “Crime

Prediction Using Machine Learning: A Comparative

Analysis,” Journal of Computer Science, vol. 19, no. 9,

pp. 1170–1179, 2023, doi:

10.3844/JCSSP.2023.1170.1179.

[10] X. Guo and P. Hao, “Using a random forest model to

predict the location of potential damage on asphalt

pavement,” Applied Sciences (Switzerland), vol. 11,

no. 21, Nov. 2021, doi: 10.3390/app112110396.

[11] I. Markoulidakis and G. Markoulidakis, “Probabilistic

Confusion Matrix: A Novel Method for Machine

Learning Algorithm Generalized

Performance Analysis,”

Technologies (Basel), vol. 12, no. 7, Jul. 2024, doi:

10.3390/technologies12070113.

[12] N. Papadakis, N. Koukoulas, I. Christakis, I.

Stavrakas, and D. Kandris, “An iot-based participatory

antitheft system for public safety enhancement in

smart cities,” Smart Cities, vol. 4, no. 2, pp.

919–937, Jun. 2021, doi:

10.3390/smartcities4020047.

[13] A. R. Khalid, N. Owoh, O. Uthmani, M. Ashawa,

J. Osamor, and J. Adejoh, “Enhancing Credit Card

Fraud Detection: An Ensemble Machine Learning

Approach,” Big Data and Cognitive Computing, vol.

8, no. 1, Jan. 2024, doi: 10.3390/bdcc8010006.

[14] S. Ibrahim, “Improving Land Use/Cover Classification

Accuracy from Random Forest Feature Importance

Selection Based on Synergistic Use of Sentinel Data

and Digital Elevation Model in Agriculturally

Dominated Landscape,” Agriculture (Switzerland),

vol. 13, no. 1, Jan. 2023, doi:

10.3390/agriculture13010098.

[15] R. Natras, B. Soja, and M. Schmidt, “Ensemble

Machine Learning of Random Forest, AdaBoost and

XGBoost for Vertical Total Electron Content

Forecasting,” Remote Sens (Basel), vol. 14, no. 15,

Aug. 2022, doi: 10.3390/rs14153547.

[16] E. D. Madyatmadja, C. P. M. Sianipar, C. Wijaya, and

D. J. M. Sembiring, “Classifying Crowdsourced

Citizen Complaints through Data Mining: Accuracy

Testing of k-Nearest Neighbors, Random Forest,

Support Vector Machine, and AdaBoost,” Informatics,

vol. 10, no. 4, Dec. 2023, doi:

10.3390/informatics10040084.

[17] D. Božić, B. Runje, D. Lisjak, and D. Kolar, “Metrics

Related to Confusion Matrix as Tools for Conformity

Assessment Decisions,” Applied Sciences

(Switzerland), vol. 13, no. 14, Jul. 2023, doi:

10.3390/app13148187.

[18] O. R. Olaniran, A. R. R. Alzahrani, and M. R.

Alzahrani, “Eigenvalue Distributions in Random

Confusion Matrices: Applications to Machine

Learning Evaluation,” Mathematics, vol. 12, no. 10,

May 2024, doi: 10.3390/math12101425.

[19] A. Kowalska, R. Banasiak, J. Stańdo, M. Wróbel-

Lachowska, A. Kozłowska, and A. Romanowski,

“Study on Using Machine Learning-Driven

Classification for Analysis of the Disparitiesbetween Categorized Learning Outcomes,”

Electronics (Switzerland), vol. 11, no. 22, Nov.

2022, doi: 10.3390/electronics11223652.

[20] R. Bian et al., “Evaluation of Three Algorithms

and Forest Fire Risk Prediction in Zhejiang

Province of China,” Forests, vol. 15, no. 12, Dec.

2024, doi: 10.3390/f15122146.

Downloads

Published

2025-12-01