Identification of residential property sub-markets using evolutionary and neural computing techniques

This paper expands on previous work considering methods of stratifying prop erty clam in order to enhance its susceptibility to modelling for mortgage value estimation. Previous work [1] considered a clustering approach using a Kuhonen Self-Organising Map (SOM) to stratify the training data prior to training a suite of MLPs. Although the results were encouraging, the approa ch suffers from its estimation of trainability post-clustering, The followi ng method ameliorates the approach by replacing the static clustering step with a dynamic genetic algorithm implementation. The results show a healthy improvement in accuracy over the non-stratified approah, and a more consis tent level of accuracy compared rt with the Kohonen SOM approach. The paper concludes by analysing the underlying content of the derived stratas. thus providing a 'human readable' element to the approach that enhances its pot ential for acceptance by valuation institutions for as a complementary tech nique to traditional valuation methods.