Abstract
Automated valuation models are increasingly used in appraisals. In some circumstances, their use provides accurate estimates with advantages in terms of time and cost of the process. Besides the programming capability, the reliability of an automated model depends on the data it has to train and verify its outcomes. In literature, many researches test the predictive capabilities of models without investigating whether similar performance would have been achieved with less data. The issue is crucial for evaluators, who aim to optimise effectiveness (accuracy) while reducing cost (data retrieval) in order to gain a competitive advantage over the industry. The research aims to test whether there is a minimum dataset size with which AVMs achieve their maximum performance. Tests were conducted on increasing sizes of the dataset in order to observe the behaviour of the models as the number of data increases. Three econometric models (Linear, polynomial and logarithmic regression) and three machine learning models (Regression tree, Random forest and Nearest neighbors) were tested. The results confirm that there is a minimum dataset size only for the machine learning models, whereas the hedonic models show little correlation with the amount of data. However, the degree of accuracy of the models seems to depend not only on the number of samples but also on the amount and type of predictors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baldominos A, Blanco I, Moreno A, Iturrarte R, Bernardez O, Afonso C (2018) Identifying real estate opportunities using machine learning. Appl Sci 8
Bisello A, Antoniucci V, Marella G (2020) Measuring the price premium of energy efficiency: a two-step analysis in the Italian housing market. Energy Build 208
Ceh M, Kilibarda M, Lisec A, Bajat B (2018) Estimating the performance of random forest versus multiple regression for predicting prices of the apartments. Int J Geo-Inform 7(5)
Cajias M (2018) Is there room for another hedonic model? The advantages of the GAMLSS approach in real estate research. J Eur Real Estate Res 11(2)
Do AQ, Grudnitski G (1992) A neural network approach to residential property appraisal. The Real Estate Appraiser 58
Glumac B, Des Rosiers F (2020) Practice briefing—automated valuation models (AVMs): their role, their advantages and their limitations. J Property Invest Finance (ahead-of-print)
Kauko T, D’Amato M (2008) Mass appraisal methods. Wiley Blackwell
Kok N, MartÃnez-Barbosa CA, Koponen EL (2017) Big data in real estate? From manual appraisal to automated valuation. J Portfolio Manage 43(6)
Lowies GA, Hall JH, Cloete CEC (2015) The role of market fundamentals vs Market sentiment in property investment decision-making in South Africa. J Real Estate Lit 23(2)
Mangialardo A, Micelli E (2019) Off-site retrofit to regenerate multi-family homes: evidence from some European experiences. Smart Innov Syst Technol 101
Mangialardo A, Micelli E (2020) Reconstruction or reuse? How real estate values and planning choices impact urban redevelopment. Sustainability (Switzerland) 12(10)
Matysiak G (2017) Report for TEGoVA the accuracy of automated valuation models (AVMs). https://www.tegova.org/data/bin/a591190c05b2c3_Geoge_Matysiak_Valuation_Report.pdf. Last access: 20th Jan 2021
McCluskey WJ, McCord M, Davis PT, Haran M, McIlhatton D (2013) Prediction accuracy in mass appraisal: a comparison of modern approaches. J Property Res 30(4)
Metzner S, Kindt A (2018) Determination of the parameters of automated valuation models for the hedonic property valuation of residential properties: a literature-based approach. Int J Housing Markets Anal 11(1)
Mullainathan S, Spiess J (2017) Machine learning: an applied econometric approach. J Econ Perspect 31(2)
Napoli G, Giuffrida S, Trovato MR (2019) A paradigm interpreting the city and the analytic network process for the management of urban transformations. Smart Innov Syst Technol 100
Nguyen N, Cripps A (2001) Predicting housing value: a comparison of multiple regression analysis and Artificial neural networks. J Real Estate Res 22(3)
Valier A (2020) Who performs better? AVMs vs hedonic models. J Property Invest Financ 38(3)
Valier A, Micelli E (2020) Automated models for value prediction: a critical review of the debate [I modelli automatici per la predizione del valore: Una rassegna critica del dibattito]. Valori e valutazioni 24
Wyman D, Seldin M, Worzala E (2011) A new paradigm for real estate valuation ? J Property Invest Financ 29 (4/5)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Valier, A. (2024). How Many Data for a Reliable Assessment? Accuracy of Models and Number of Comparables in Automated Valuation Models (AVMs). In: Giuffrida, S., Trovato, M.R., Rosato, P., Fattinnanzi, E., Oppio, A., Chiodo, S. (eds) Science of Valuations. Green Energy and Technology. Springer, Cham. https://doi.org/10.1007/978-3-031-53709-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-53709-7_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53708-0
Online ISBN: 978-3-031-53709-7
eBook Packages: EnergyEnergy (R0)