This paper starts with considering the extent of archaeological predictive modelling in Europe and the various different techniques used. One of the main criticisms against archaeological predictive modelling is that it is a ‘Black Box’ technique and this paper suggests a possible way to make the procedure more transparent to the non-technical user. It is hoped that this would make the technique more acceptable to the archaeological community and would allow a model to be interrogated and tested by others. The paper stresses that archaeological predictive models should be tested against new archaeological data, not used to make the model, as opposed to how well the model predicts its own input data. The paper also suggests a possible independent way of testing archaeological predictive models, in an attempt to gain credibility for the use of the technique for cultural heritage management. It appears that there are as many archaeological predictive models as there are methods to produce them. This paper argues that whilst it would be impractical to write standards that cover every technique, it would be advantageous to start thinking now about standards for the output of these models, so that one model could be compared against other model.