Achieving property valuation accuracy in developing countries: the implication of data source

The demand for accurate property value estimation by valuation report end users has led to a shift towards advanced property valuation modelling techniques in some property markets and these require a sizeable number of data set to function. In a situation where there is a lack of a centralised transaction data bank, scholars and practitioners usually collect data from different sources for analysis, which could affect the accuracy of property valuation estimates. This study aims to establish the suitability of different data sources that are reliable for estimating accurate property values.

This study adopts the Lagos metropolis property market, Nigeria, as the study area. Transaction data of residential properties are collected from two sources, i.e. from real estate firms (selling price) and listing prices from an online real estate company. A portion of the collected data is fitted into the artificial neural network (ANN) model, which is used to predict the remaining property prices. The holdout sample data are predicted with the developed ANN models. Thereafter, the predicted prices and the actual prices are compared so as to establish which data set generates the most accurate property valuation estimates.

It is found that the listing data (listing prices) produced an encouraging mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) values compared with the firms’ data (selling prices). An MAPE value of 26.93 and 29.96 per cent was generated from the listing and firms’ data, respectively. A larger proportion of the predicted listing prices had property valuation error of margin that is within the industry acceptable standard of between ±0 and 10 per cent, compared with the predicted selling prices. Also, a higher valuation accuracy was recorded in properties with lower values, compared with expensive properties.

The opaqueness in real estate transactions consummated in developing nations could be attributed to why selling prices (data) could not produce more accurate valuation estimates in this study than listing prices. Despite the encouraging results produced using listing prices, there is still an urgent need to maintain a robust and quality property data bank in developing nations, as obtainable in most developed nations, so as to achieve a sustainable global property valuation practice.

This study does not investigate the relationship between listing prices and selling prices, which has been conducted in previous studies, but examines their suitability to improve property valuation accuracy in an emerging property market. The findings of this study would be useful in property markets where property transaction data bank is not available.