Methods used to link crimes using behaviour: A literature review

This paper reviews the crime linkage literature to identify how data were pre-processed for analysis, methods used to predict linkage status/series membership, and methods used to assess the accuracy of linkage predictions. Thirteen databases were searched, with 77 papers meeting the inclusion/exclusion criteria. Methods used to pre-process data were human judgement, similarity metrics (including machine learning approaches), spatial and temporal measures, and Mokken Scaling. Jaccard's coefficient and other measures of similarity (e.g., temporal proximity, inter-crime distance, similarity vectors) are the most common ways of pre-processing data. Methods for predicting linkage status were varied and included human (expert) judgement, logistic regression, multi-dimensional scaling, discriminant function analysis, principal component analysis and multiple correspondence analysis, Bayesian methods, fuzzy logic, and iterative classification trees. A common method used to assess linkage-prediction accuracy was to calculate the hit rate, although position on a ranked list was also used, and receiver operating characteristic (ROC) analysis has emerged as a popular method of assessing accuracy. •Behaviour can be used to link crime series•Research has examined the accuracy of crime linkage using different methods•Pre-processing of data is required before making predictions•Methods for predicting linkage status are varied•Receiver Operating Characteristic (ROC) is a popular method of assessing accuracy•Accuracy estimation is vital for assessing the validity of crime linkage advice