Ibrahim, Affa Lelira (2026) Implementasi Mixed Geographically and Temporally Weighted Regression (Mixed GTWR) dengan Robust Estimator untuk Prediksi Tingkat Kejahatan Di Jawa Timur. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
Cover.pdf Download (1MB) | Preview |
|
|
Text (Bab 1)
BAB 1.pdf Download (336kB) | Preview |
|
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Bab 2)
BAB 2.pdf Restricted to Repository staff only until 6 May 2028. Download (908kB) |
|
|
Text (Bab 3)
BAB 3.pdf Restricted to Repository staff only until 6 May 2028. Download (668kB) |
|
|
Text (Bab 4)
BAB 4.pdf Restricted to Repository staff only until 6 May 2028. Download (2MB) |
|
|
Text (Bab 5)
BAB 5.pdf Download (342kB) | Preview |
|
|
Text (Daftar Pustaka)
DAFTAR PUSTAKA.pdf Download (193kB) | Preview |
|
|
Text (Lampiran)
LAMPIRAN.pdf Restricted to Repository staff only Download (428kB) |
Abstract
Socio-economic developments in Indonesia pose significant challenges to security stability, as reflected in the 52nd ranking in the 2023 Global Peace Index. East Java Province recorded the third highest number of crimes in Indonesia in 2024 with 60,102 cases. The phenomenon of crime has a high complexity because it is influenced by spatial and temporal heterogeneity, where the relationship between socio-economic factors differs between regions and times. The research aims to implement a model that is able to predict crime rates by considering heterogeneity and deal with the existence of outliers that can reduce the accuracy of estimates. The method used is Mixed Geographically and Temporally Weighted Regression with the Robust MM-Estimator (Robust Mixed GTWR) approach. The model combines global and local variables and uses a stable estimation procedure for extreme data. The variables used include the percentage of the poor population, the Human Development Index (HDI), the Open Unemployment Rate (OUT), the police ratio, and the Gini ratio in East Java for the 2020–2024 period. The results showed that there were 15 outliers in the data. The evaluation of the Robust Mixed GTWR model yielded a value of 0.84 and an MSE of 1912.247. The implementation of R^2 robust estimators has proven to be effective in increasing model stability, as can be seen from the Gini ratio variable that was previously insignificant in the Mixed GTWR model to be significant in the robust model. These results contribute to the achievement of the 16th SDGs target and support the 2025–2045 RPJPN agenda through the provision of a more accurate and stable crime prediction model.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Affa Lelira Ibrahim | ||||||||||||
| Date Deposited: | 19 May 2026 06:27 | ||||||||||||
| Last Modified: | 19 May 2026 06:27 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/51596 |
Actions (login required)
 |
View Item |