Naslov
Application of mathematical models in detecting the spatial mobility patterns of robber perpetrators for the City of Zagreb

Autori
Butorac, Ksenija ; Maurer, Dubravka ; Gajski, Dubravko

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, neobjavljeni rad, znanstveni

Skup
The 21st Annual (online) Conference of the European Society of Criminology - EUROCRIM

Mjesto i datum
Online, 08.09.2021. - 10.09.2021

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
geographical profiling, robber perpetrators, distance decay function, multicriteria analysis

Sažetak
This paper presents the achievements of the project: ‘Geographic profiling of robbers in the City of Zagreb for 2018’. Geographic profiling is the methodology which attempts to describe the spatial movement of the perpetrators by applying certain mathematical models. Distance decay function is the base of mathematical models that are applied when creating the geographic profile of the serial perpetrators. To examine the possibilities of the application for the geographic profile for the City of Zagreb, the five most frequently used distance decay functions were calibrated on the solved cases of robberies in the City of Zagreb for 2018. The spatial resolution of the obtained data has been reduced to certain neighborhoods in Zagreb, due to the problem of the GDPR and the impossibility of obtaining the exact coordinates of the crime scenes and the residence of the offenders. In order to obtain distances, neighborhood centroids were calculated and determined as reference points. In cases where the residence and the crime location are in the same neighborhood, the neighborhood was described by a circle whose radius is taken as the reference distance. Other data such as time component, object of interest, modus of operandi, etc. are collected from the police records. The goal of this project is to obtain the optimal distance decay function that will most adequately describe the spatial movement of the robber perpetrators in the City of Zagreb. Such model would be the base for upgrades with other conditions (such as time component and socioeconomics conditions) through multicriteria analysis in GIS and as a basis for examining the possibility of further upgrading the prediction model using machine learning algorithms.

Izvorni jezik
Engleski

Znanstvena područja
Interdisciplinarne tehničke znanosti, Interdisciplinarne društvene znanosti

POVEZANOST RADA