Bayesian Journey-to-Crime Estimation: An Improvement in Geographic Profiling Methodology

A Bayesian approach to geographic profiling methodology involves updating journey-to-crime probability estimates with probabilities based on the distribution of residences of other offenders who committed crimes in the same locations. Tests were conducted on serial offenders from Baltimore County and Chicago and six different methods using five different criteria were compared. The Bayesian method was more accurate than the existing journey-to-crime methods and was as accurate as the center of minimum distance, the current best method. Suggestions for improving the methodology further are provided.