Trend Analysis and Clustering of Criminal Offences in Russia (2008-2023): Insights from Regional Crime Data

Abstract

This study investigates crime trends and regional clusters in Russia from 2008 to 2023, utilizing data mining techniques to uncover patterns and inform policy-making, particularly in the context of cyber law. Time series analysis reveals a consistent decline in overall crime rates, with theft dominating but steadily decreasing, while violent crimes such as murder show gradual declines. Through K-Means clustering, the regions are categorized into four distinct clusters, each reflecting unique socio-economic and geographic dynamics. Cluster 0 encompasses rural, low-crime regions, characterized by geographic isolation and sparse populations. Cluster 1, including urbanized and industrial regions, shows high rates of property and violent crimes. Cluster 2, represented solely by Moscow, exhibits extreme crime intensity, underlining the complexities of managing crime in a metropolitan hub. Cluster 3 features transitional regions with moderate crime levels, highlighting a mix of rural and urban influences. The findings underscore the interconnectedness of traditional crime patterns and vulnerabilities to cybercrime. Urbanized clusters face heightened exposure to digital threats, while rural regions are vulnerable to targeted scams due to limited digital infrastructure. These insights advocate for tailored legal frameworks, balancing urban-focused cybersecurity policies with rural community-based interventions. However, the study acknowledges the dataset's limitation in excluding direct cybercrime indicators, necessitating further integration with digital offense data for comprehensive insights. This research contributes to bridging the gap between traditional criminology and cyber law by emphasizing the importance of data-driven governance. By identifying regional disparities and crime dynamics, it highlights the need for adaptive legal frameworks that respond to evolving socio-economic and technological landscapes. Future work should integrate cybercrime datasets and refine clustering techniques to enhance granularity and address cross-border crime dynamics.