Solouki, Fereshteh, Shrestha, Subeksha, Homayounvala, Elaheh and Rattadilok, Prapa (2025) Investigating gendered homicide pattern in London with focus on female victims (2003-2024) using association rule mining. In: 13th International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA-2025) June 06 - 07, 2025, 6-7 June 2025, London Metropolitan University, London (UK) / Online. (In Press)
Homicide is among the most severe manifestations of violent crime, and its gendered patterns reveal critical societal vulnerabilities. Research consistently shows that women face elevated homicide risks, particularly from domestic abuse and intimate partner violence. Motivated by the urgent need to advance violence against women and girls (VAWG) prevention efforts, this study adopts a gender-sensitive, data-driven approach to uncover hidden homicide patterns in London from 2003 to 2024. A dataset of 2,934 homicide records was analysed using descriptive statistics and association rule mining (ARM). Descriptive analysis examined variations in victim age, ethnicity, domestic abuse involvement, and geographic distribution between male and female victims. ARM was applied exclusively to female homicide cases, identifying significant associations between specific Boroughs, Months, and Offence types. Notably, manslaughter cases in Hounslow, and seasonal homicide peaks in Ealing (November) and Islington (June) were uncovered, highlighting borough-specific and temporal risk patterns. The findings show that male homicides are concentrated among younger victims in public spaces, while female homicides span a broader age range and are strongly linked to domestic contexts. This study enhances understanding of gendered homicide dynamics in London and provides actionable insights for targeted VAWG prevention initiatives.
Restricted to Repository staff only until 6 October 2026.
Download (499kB) | Request a copy
![]() |
View Item |