Property Valuations in Times of Crisis: Artificial Neural Networks and Evolutionary Algorithms in Comparison

Abstract

Abstract. In the current economic situation, characterized by a high uncertainty in the appraisal of property values, the need of "slender" models able to operate even on limited data, to automatically capture the causal relations between explanatory variables and selling prices and to predict property values in the short term, is increasingly widespread. In addition to Artificial Neural Networks (ANN), that satisfy these prerogatives, recently, in some fields of Civil Engineering an hybrid data-driven technique has been implemented, called Evolutionary Polynomial Regression (EPR), that combines the effectiveness of Genetic Programming with the advantage of classical numerical regression. In the present paper, ANN methods and the EPR procedure are compared for the construction of estimation models of real estate market values. With reference to a sample of residential apartments recently sold in a district of the city of Bari (Italy), two estimation models of market value are implemented, one based on ANN and another using EPR, in order to test the respective performance. The analysis has highlighted the preferability of the EPR model in terms of statistical accuracy, empirical verification of results obtained and reduction of the complexity of the mathematical expression.

An Analysis of the Influence of Property Tax on Housing Prices in the Apulia Region (Italy)

“…In particular, Morano et al [55] have used the EPR method for an analysis of the interdependencies of the property market with zonal and socio-economic variables in the municipalities of the region of Puglia (Italy). Tajani et al have carried out a first experimentation of this technique with mass appraisal purposes, comparing it with the Artificial Neural Networks (ANN) method [56] and the hedonic price model [57]. There are not other applications to the property market, although the EPR method is characterized by interesting and unexplored potentialities.…”

An Analysis of the Methods Applied for the Assessment of the Market Value of Residential Properties in Italian Judicial Procedures

“…Furthermore, a consistent number of evaluation reports does not clearly explain the method applied for the market value determination. The IVS claim that the information sources consulted in the assessment path have to be made explicit, in order to verify their robustness and reliability [27]. Taking into account the national context of the analysis, the Italian Property Valuation Standards [28] should be recalled, that promotes the IVS use and define an ethical and deontological code, by pointing out the importance to overcome the expertise approach based on the valuers knowledge, as this can be verified exclusively through the comparison with assessments carried out by other valuers.…”

Automated Valuation Methods through the Cost Approach in a BIM and GIS Integration Framework for Smart City Appraisals

“…The use of sophisticated fitting techniques can account for different functional forms or, in some cases, the complete lack of functional relationships. Spline regressions, nonparametric regressions, and autoregressive techniques are three of such examples [15][16][17]. Incorporating spatial information in pricing models through the use of direct spatial modeling with Cartesian coordinates [18], geostatistical models [19,20], or response surfaces [21] has improved the precision of price estimates.…”