Prediction accuracy in mass appraisal: a comparison of modern approaches
Точность прогнозирования при массовой оценке: сравнение современных подходов
2013-04-14
SCID: 54.1/zvg5qdjx
Discuss with AI
artificial neural networkscomputer-assisted mass appraisalgeographically weighted regressionhedonic pricing modelmass appraisal
Figures from the paper
Abstract (AI)
The advancement of computational software within the last decade has facilitated enhanced uptake of mass appraisal methodologies by the valuation and prediction accuracy in computer-assisted mass appraisal community for price modelling, estimation and tribunal defence. Applying a sample of 2694 residential properties, this paper assesses and analyses a number of geostatistical approaches relative to an artificial neural network (ANN) model and the traditional linear hedonic pricing model for mass appraisal valuation accuracy and price estimation purposes. The findings demonstrate that the geostatistical localised regression approach is superior in terms of model explanation, reliability and accuracy. ANNs can be shown to perform very well in terms of predictive power, and therefore valuation accuracy, outperforming the traditional multiple regression analysis (MRA) and approaching the performance of spatially weighted regression approaches. However, ANNs retain a ‘black box’ architecture that limits their usefulness to practitioners in the field. In relation to cost-effectiveness and user-friendly applicability for the valuation community, the MRA approach outperforms the ‘black box’ nature of the ANN technique, with the geographically weighted regression approach providing the best balance of outright performance and transparency of methodology. It is this spatially weighted approach utilising absolute location which appears to represent the way forward in developing the practice of mass appraisal.
Key Findings
1
Artificial neural networks achieve high predictive power, outperform multiple regression analysis, and approach spatially weighted regression performance.
2
Geographically weighted regression offers the best balance between predictive performance and methodological transparency, supporting its future use in mass appraisal.
3
Geostatistical localized regression provides the strongest overall model explanation, reliability, and valuation accuracy among the evaluated approaches.
4
The black-box architecture of artificial neural networks limits their practical usefulness and transparency for valuation professionals.
5
Using 2,694 residential properties, the study compares geostatistical approaches, artificial neural networks, and traditional linear hedonic models for mass appraisal accuracy.
Research Object
Mass appraisal valuation of 2,694 residential properties using geostatistical, artificial neural network, and linear hedonic pricing models
Research Subject
Comparative prediction, valuation accuracy, explanatory power, reliability, transparency, and cost-effectiveness of alternative price-modelling approaches
Publication Details
Publication Date
2013-04-14
Journal
Publisher
ISSN
Cited by
196
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai1
Cited by13
Mass Appraisal Models of Real Estate in the 21st Century: A Systematic Literature Review2019
Improving property valuation accuracy: a comparison of hedonic pricing model and artificial neural network2018
Interpretable machine learning for real estate market analysis2022
Estimation and updating methods for hedonic valuation2019
The Complex Neural Network Model for Mass Appraisal and Scenario Forecasting of the Urban Real Estate Market Value That Adapts Itself to Space and Time2021
Comparison of expert algorithms with machine learning models for real estate appraisal2017
Artificial Neural Networks and the Mass Appraisal of Real Estate2018
Property Mass Valuation on Small Markets2021
Hedonic Valuation of Real Estate Properties in Nigeria2018
Neural networks support vector machine for mass appraisal of properties2020
Model agnostic interpretable machine learning for residential property valuation2023
Factors affecting land value in an Indian city2022
Methods and models of real estate mass appraisal2022