IDENTIFYING THE RESIDENTIAL LOCATION OF RAPISTS

The spatial offence behaviour of 45 British serial rapists was examine d in order to generate a predictive model, of use to criminal investig ators. Two alternative hypotheses were explored. One predicted that ra pists would commute into an area to carry out their offence. The secon d predicted that they would ''maraud'' out from a fixed location. Of t he 45 offenders, 39 fitted the ''maurader'' hypothesis. However, the a rea covered by this model was an average of nearly 180 square miles. A second complementary theory, developed from facets of offenders' back grounds, was therefore used to refine the predictions of distance trav elled to and between offences. This enabled the size of the residentia l zone predicted from the marauder model to be reduced to a mean area of just over ten square miles. Tests of these models, combined into a small scale expert system, predicted the correct area for 82% of the c ases. Suggestions for the further development of this expert system ar e discussed.