The spatiotemporal patterns and driving factors of cybercrime in the UK during the COVID-19 pandemic

Cybercrime is a complex human behavior and social phenomenon. The COVID-19 pandemic has significantly altered socioeconomic activities, potentially causing changes in crime patterns. However, there has been limited research on how the interaction between the pandemic and socioeconomic factors affects cybercrime. Here we explore the spatiotemporal patterns of police-recorded cybercrime, including fraud and cyber-dependent crime, and employ a machine learning approach to assess the correlation of various factors on cybercrimes at the level of internal regions and police areas within the United Kingdom. Our results show that fraud and cyber-dependent crime are mainly concentrated in London and the southeast region of England. Moreover, following the implementation of the third national lockdown, these areas experienced a noticeable increase, while changes in other regions were not as pronounced. The spatial autocorrelation analysis further suggests that there are significant spatial heterogeneities among regions, with spatiotemporal hotspots centered around London and cold spots mainly concentrated in the northeast of England. Additionally, we found that the identified patterns of fraud and cyber-dependent crime are primarily associated with socioeconomic factors, followed by government containment measures and mobility factors. These findings can help law enforcement and regulatory agencies better understand the social-environmental factors contributing to the prevalence of cybercrime within those areas.