Publicaties

The present study compares the performance of three different supervised machine learning methods, namely an Ensemble Neural Network algorithm (ENN), a Random Forest algorithm (RF), and a K-Nearest Neighbor algorithm (KNN), in predicting residential burglary hot spots across different cities in Europe, i.e., Brussels, Vienna and London. Crime and crime-supporting data are collected for the three cities, spanning the period 2014-2016. The data ...

PurposeIn this empirical study, we assessed the reputational consequences of a large-scale football fraud scandal by measuring fans' integrity perceptions. More specifically, we targeted inherent, personal, organizational, and procedural integrity.MethodologyWe used a cross-sectional survey distributed through a Belgian sports newspaper to reach our respondents (n = 1693), that were divided into non-football fans, average, and loyal football ...

In deze studie werd crime scripting toegepast op het fenomeen woninginbraak, met als doel een diepgaander inzicht te verwerven in de verschillende modi operandi die inbrekers hanteren. Het achterliggende doel was om na te gaan in hoeverre er verschillende verschijningsvormen bestaan van woninginbraak en in welke mate deze gebruikt kunnen worden in onderzoek en politiepraktijken met betrekking tot de tijdruimtelijke spreiding van criminaliteit. ...

This study provides an overview of the modus operandi used in one of the biggest fraud cases in Belgian football, known as the Zheyun Ye case. The case consists of several phenomena related to betting-related match-fixing. Given the fact that money laundering and tax fraud are often essential factors in betting-related match-fixing schemes and the fragmented research on these types of financial misconducts in sports, we analyzed the modus ...

This study examines the potential of alternative micro-geographic units of analysis compared to the widely used rectangular grid for predicting (monthly) micro-geographic crime risks using a machine learning approach. Specifically, this study compares the prediction performance of machine learning models (XGBoost) in deriving monthly micro-geographic risk predictions for three crime types across rectangular and hexagonal grids of varying ...

In this study, we provide a nuanced perspective on a sub-type of match-fixing, called non-betting-related match-fixing (NBMF). Using a cross-sectional survey, we measured the prevalence and motives behind NBMF in Belgian amateur football and tennis. Additionally, we conducted a thorough study of the regulatory documents of the relevant (sports) organizations to examine the sanctionability of different types of NBMF by analyzing their ...

The adoption of new data-driven methods is increasingly transforming both public and private sectors. Within the context of law enforcement, the increasing prevalence of big data and big data analytics is significantly reshaping decision-making processes at both operational and strategic levels. The emergence of ‘big data policing’ as a multifaced concept is progressively becoming a substantive approach to various aspects of policing and social ...