ABSTRACT
This chapter provides an examination of the various techniques available for mass appraisal, from multiple regression analysis through to artificial neural networks and discusses methodological considerations relating to the dataset and evaluation of predictive accuracy. It aims to evaluate the application of three of the techniques in an empirical analysis and examines the robustness of two of the better techniques under more stringent conditions. These techniques are: neural networks, expert systems and multiple regression. In terms of mass appraisal one of the most important advances was the introduction of regression as a tool for the prediction of value. Adaptive Estimation Procedure (AEP) is a fairly recent development in the field of value prediction. AEP is seen as a potential alterative to regression analysis. An expert system is a tool implemented in computerized form which performs the role of an expert or carries out a task which requires expertise.
