Tagging Banksy: using geographic profiling to investigate a modern art mystery

Abstract

The pseudonymous artist Banksy is one of the UK’s most successful contemporary artists, but his identity remains a mystery. Here, we use a Dirichlet process mixture (DPM) model of geographic profiling, a mathematical technique developed in criminology and finding increasing application within ecology and epidemiology, to analyse the spatial patterns of Banksy artworks in Bristol and London. The model takes as input the locations of these artworks, and calculates the probability of ‘offender’ residence across the study area. Our analysis highlights areas associated with one prominent candidate (e.g., his home), supporting his identification as Banksy. More broadly, these results support previous suggestions that analysis of minor terrorism-related acts (e.g., graffiti) could be used to help locate terrorist bases before more serious incidents occur, and provides a fascinating example of the application of the model to a complex, real-world problem.

Keywords:

• Bayesian statistics
• criminology
• Dirichlet process mixture model
• geographic profiling
• graffiti