OPTIMALISASI PENENTUAN DAERAH RAWAN KRIMINAL WILAYAH POLRESTABES PALEMBANG DENGAN PENDEKATAN CLUSTERING BERBASIS MACHINE LEARNING

Lenny Ramadhona; Yesi Novaria Kunang; M. Izman Herdiansyah; A. Haidar Mirza

doi:10.31539/8mgvem13

Authors

Lenny Ramadhona Universitas Binadarma
Yesi Novaria Kunang Universitas Binadarma
M. Izman Herdiansyah Universitas Binadarma
A. Haidar Mirza Universitas Binadarma

DOI:

https://doi.org/10.31539/8mgvem13

Abstract

Kriminalitas merupakan masalah sosial yang meningkat di kota besar seperti Palembang. Polrestabes Palembang mencatat banyak kasus tiap tahun dengan variasi lokasi, waktu, dan jenis kejahatan, menyulitkan masyarakat untuk mendapatkan informasi mengenai lokasi kawasan rawan kejahatan dan lokasi kawasan aman. Sebagai solusi dari masalah tersebut, dibutuhkan sebuah sistem yang menggunakan pendekatan Machine Learning untuk memetakan daerah rawan kriminal dengan lebih efektif dalam mengoptimalkan penentuan daerah rawan kriminal.

Keywords: Analysis of Crime-prone Areas in Palembang Metropolitan Police Region Using Kernel Density Estimation and K- Means Clustering Methods

References

Anggoro JW, Awaluddin M, & Nugraha AL.(2019). Zoning of motor vehicle theft (curanmor) areas in Semarang City using the cluster method.

Dr. Sidiq UMA, & Choiri DMM.(2019). Qualitative research methods in education Ponorogo CV. Nata Karya.

Herviani V, & Febriansyah.(2016). Accounting Research Journal.

Juita I.(2021). Spatial analysis of motor vehicle theft (curanmor) using the nearest neighbor analysis and kernel density methods in Bandar Lampung City. Journal 1-23.

Mulyati S.(2015). Application of data mining using the clustering method for grouping bird delivery data. Proceedings of the National Scientific Seminar on Computer Technology (Senatkom),30–35

Nanda CA, Nugraha AL, & Firdaus, HS.(2019). Analysis of crime-prone areas using the kernel density method in the jurisdiction of the Semarang City Police. Undip Geodesy Journal, 8(4), 50–58.

Silverman BW.(2018). Density estimation for statistics and data analysis. Routledge.

Rafi Nahjan M, Heryana N & Voutama, A.(2023). Implementation of Rapidminer using the K- Means clustering method for sales analysis at the Oj Cell Store.

Sopyan Y, Lesmana, AD & Juliane C.(2022). Analysis of the K-Means algorithm and Davies Bouldin Index in finding the best cluster of divorce cases in Kuningan Regency. Building of Informatics, Technology and Science (BITS), 4(3), 1464–1470. Available at: https://doi.org/10.47065/bits.v4i3.2697.

Stedila S, Astuti R & Basysyar FM.(2024). Application of data mining clustering using the K Means method to crime data at the Kuningan Regency Police.

Sukaridhoto S & STP.(2019). Playing with the Internet of Things & Big Data. Sustainability (Switzerland), 11(1), 1–14. Available at: [URL].

Unayah N & Sabarisman M.(2016). The Phenomenon of Juvenile Delinquency and Crime. Sosio

Informa, 1(2), 121–140. Available at: https://doi.org/10.33007/inf.v1i2.142. Watrianthos R. et al.(2023). Mapping Crime Rates in Indonesia: Spatial Analysis Using a GIS Approach at the Provincial Level.