Towards an intelligent residential appraisal model

摘要: In the UK, and indeed in many countries, Direct Capital Comparison (DCC) remains central to practice of residential property valuers. Theoretically well founded, statistically or heuristically-based alternatives, usually embodying regression techniques, have failed penetrate professional despite long pedigrees. For several years, neural networks, which values are not so much derived assigned but discovered, also been propounded as potential alternatives. Yet DCC clings its pre-eminent position because it is readily understood thought produce more accurate results. order improve upon DCC, complementary alternative methods will need enhance accuracy, be equally intelligible transparent. This paper reports empirical findings, discusses some obstacles that overcome constituents may comprise an improved model.