To read the full version of this content please select one of the options below:

High‐tech valuation: should artificial neural networks bypass the human valuer?

Margarita M. Lenk (Colorado State University, Fort Collins, Colorado, USA)
Elaine M. Worzala (Colorado State University, Fort Collins, Colorado, USA)
Ana Silva (Colorado State University, Fort Collins, Colorado, USA)

Journal of Property Valuation and Investment

ISSN: 0960-2712

Article publication date: 1 March 1997

Abstract

Compares the predictive performance of artificial neural networks to hedonic pricing models, a more traditional valuation tool. The results document similar predictive performance evidenced from both techniques, which contradicts some of the earlier studies which support a position of artificial neural network superiority. Demonstrates that at least 18 per cent of the “normal” property predictions and over 70 per cent of the “outlier” property predictions contained valuation errors greater than 15 per cent of the actual sales price. The combination of these substantial errors and the model‐optimization costs incurred motivate a message of caution before artificial neural networks are adopted by the real estate valuation and/or lending industries.

Keywords

Citation

Lenk, M.M., Worzala, E.M. and Silva, A. (1997), "High‐tech valuation: should artificial neural networks bypass the human valuer?", Journal of Property Valuation and Investment, Vol. 15 No. 1, pp. 8-26. https://doi.org/10.1108/14635789710163775

Publisher

:

MCB UP Ltd

Copyright © 1997, MCB UP Limited