Hybrid predictions of the homogenous properties’ market value with the use of ann

Authors

  • Hubert Anysz Warsaw University of Technology, Faculty of Civil Engineering, Warsaw, Poland
  • Monika Podwórna Wrocław University of Science and Technology, Faculty of Civil Engineering , Wrocław, Poland
  • Nabi Ibadov Warsaw University of Technology, Faculty of Civil Engineering, Warsaw, Poland
  • Kunibert Lennerts Karlsruhe Institute of Technology, Institute of Technology and Management in Construction, Karlsruhe, Germany
  • Kostiantyn Dikarev Prydniprovska State Academy of Civil Engineering and Architecture, Department of Construction Technology, Dnipro, Ukraine

DOI:

https://doi.org/10.24425/ace.2021.136474

Keywords

real estate valuation, artificial neural network, multilayer perceptron, comparative approach, machine learning, hybrid model

Abstract

The homogenous properties – as flats are – have the set of key features that characterizes them. The area of a flat, the number of rooms and storey number where it is located, the technical state of a building, and the state of the vicinity of the blocks of flats assessed. The database comprises 222 flats with their transaction prices on the secondary estate market. The analysed flats are located in a certain quarter of Wrocław city in Poland. The database is large enough to apply machine learning for successful price predictions. Their close locations significantly lower the influence of clients’ assessments of the attractiveness of the location on the flat’s price. The hybrid approach is applied, where classifying precedes the solution of the regression problem. Dependently on the class of flats, the mean absolute percentage error achieved through the calculations presented in the article varies from 4,4 % to 7,8 %. In the classes of flats where the number of cases doesn’t allow for machine predicting, multivariate linear regression is applied. The reliable use of machine learning tools has proved that the automated valuation of homogenous types of properties can produce price predictions with the error low enough for real applications.

References

1. R. Gaca, “Parametric and non-parametric statistical methods in the assessment of the effect of property attributes on prices”, Real Estate Management And Valuation 2, 28, 9-15, 2018

2. R. Gaca, “Comparative appraisal models”, Rzeczoznawca majątkowy 2/2018, 8-13, 2018

3. International valuation standards (IVS) 2017

4. Ustawa z dnia 21 sierpnia 1998 r. o gospodarce nieruchomościami (Act of 21 August 1998 on real estate management).

5. TEGOVA European Valuation Standards, EVS 2016

6. E. Jahanshiri, T. Buyong, A.R.M. Shariff, “A Review of Property Mass Valuation Models”, Pertanika J. Sci. & Technol. 19, 23-30, 2011

7. S. Kokot, S. Gnat, Simulative verification of the possibility of using multiple regression models for real estate appraisal, Real Estate Management and Valuation, vol. 27, no. 3, pp. 109-123, 2019

8. M. Renigier-Biłozor, “Application of the rough set theory to mass appraisal of real estate on small markets”, Acta Scientiarum Polonorum. Administatio Locorum 7/3, 35-51, 2008

9. Rozporządzenie Rady Ministrów z dnia 21 września 2004 r. w sprawie wyceny nieruchomości i sporządzania operatu szacunkowego (Ordinance of the Council of Ministers of 21 September 2004 on the valuation of real estate and the preparation of an appraisal report).

10. M. Podwórna, W. Mironowicz, “Praktyczne aspekty oceny stopnia zużycia obiektów budowlanych, dla potrzeb wyceny nieruchomości”, Rzeczoznawca Majątkowy Nr 1/2017 (93) s. 8-13, 2017

11. M.T. Hagan, H.B. Demuth, M.H. Beale, O. De Jesús, Neural Network Design; Martin Hagan: Lexington, KY, USA, 2014.

12. M. Kaftanowicz, M. Krzemiński, Multiple-criteria Analysis of Plasterboard Systems, Procedia Engineering 111:364-370, 2015, doi: 10.1016/j.proeng.2015.07.102

13. H. Anysz, A. Zbiciak, N. Ibadov, The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks, Procedia Engineering 153, 2016, doi: 10.1016/j.proeng.2016.08.08

14. I. Foryś, R. Gaca, Theoretical and practical aspects of qualitative variable descriptions of residential property valuation multiple regression models. In: Proceedings, Foundation of the Cracow University of Economics, Cracow, 978-83-65173-48-5, pp 36-44, 2016

15. W.J. McCluskey, R.A. Borst, The Theory and Practice of Comparable Selection in Real Estate Valuation. In: d'Amato M., Kauko T. (eds) Advances in Automated Valuation Modeling. Studies in Systems, Decision and Control, vol 86. Springer, 2017

16. M. Ciuna, M. De Ruggiero, B. Manganelli, F. Salvo, M. Simonotti, Automated Valuation Methods in Atypical Real Estate Markets Using the Mono-parametric Approach. In: Gervasi O. et al. (eds) Computational Science and Its Applications - ICCSA 2017. ICCSA 2017. Lecture Notes in Computer Science, vol 10406. Springer, 2017, doi: 10.1007/978-3-319-62398-6

17. F. Tajani, P. Morano, M. Locurcio, N. D’Addabbo, Property valuations in times of crisis: artificial neural networks and evolutionary algorithms in comparison. In: Gervasi, O., Murgante, B., Misra, S., Gavrilova, M.L., Rocha, A.M.A.C., Torre, C., Taniar, D., Apduhan, B.O. (eds.) ICCSA 2015. LNCS, vol. 9157, pp. 194-209. Springer, 2015. doi: 10.1007/978-3-319-21470-2

18. M. Rogalska, P. Wolski, Prognozowanie cen 1m2 mieszkania na rynku pierwotnym w Warszawie metodą uogólnionych modeli addywnych, Logistyka 6/2014, pp 9101-9110, 2014

19. M. Rogalska, Wycena nieruchomości z wykorzystaniem metody wieloczynnikowych modeli statystycznych, (chapter in:) Inżynieria Przedsięwzięć Budowlanych. Problemy Modele Metody, (edit. Sobotka A., Radziszewska-Zielina E.), KILiW PAN, 2018

20. N. Ibadov, H. Anysz, Ustalenie stopnia zużycia technicznego obiektów budowlanych w zarządzaniu nieruchomościami, Technika Transportu Szynowego. Koleje, Tramwaje, Metro 10/2013, pp. 49-56, 2013

21. B. Nowogońska, Diagnoses in the Aging Process of Residential Buildings Constructed Using Traditional Technology, Bulidings, 2019, doi: 10.3390/buildings9050126

22. B. Kutera, H. Anysz, The methodology of technical due diligence report preparation for an office, residential and industrial buildings, MATEC Web of Conferences 86:07009, 2016, doi: 10.1051/matecconf/20168607009

23. M. Juszczyk, A. Leśniak, Modelling construction site cost index based on neural network ensembles. Symmetry 11(3), 2019

24. M. Juszczyk, A. Leśniak, K. Zima, ANN Based Approach for Estimation of Construction Costs of Sports Fields, Complexity (1), 2018, doi: 10.1155/2018/7952434

25. M. Rogalska, Wieloczynnikowe modele w prognozowaniu czasu procesów budowlanych, Lublin University of Technology, Lublin 2016, ISBN: 978-83-7947-186-7

26. H. Anysz, N. Ibadov, Neuro-fuzzy predictions of construction site completion dates, Technical Transactions 6/2017, Civil Engineering, pp. 51-58, 2017, doi: 10.4467/2353737XCT.17.086.6562

27. H. Anysz, Wykorzystanie sztucznych sieci neuronowych do oceny możliwości wystąpienia opóźnień w realizacji kontraktów budowlanych, Oficyna Wydawnicza PW, Warsaw, 2017

28. L. Zajączkowski, Z. Waszczyszyn, A. Tomana, M. Jakubek, Sztuczne sieci neuronowe w wycenie działek budowlanych. (chapter in:) Konferencja Naukowa Komitetu Inżynierii Lądowej i Wodnej PAN i Komitetu Nauki PZITB (49:2003; Warszawa-Krynica), Problemy naukowo-badawcze budownictwa, ISBN 837207433X, Oficyna Wydawnicza PW, Warsaw, 2003

29. J. Morajda, Wykorzystanie perceptronowych sieci neuronowych w zagadnieniu wyceny nieruchomości. Zeszyty Naukowe Małopolskiej Wyższej Szkoły Ekonomicznej w Tarnowie, (7), 101-108, 2005

30. T. Jasiński, A. Bochenek, Prognozowanie cen nieruchomości lokalowych za pomocą sztucznych sieci neuronowych. Studia i Prace WNEiZ US, 45, 317-328, 2016, doi: 1018276/sip.2016.45/1-25

Downloads

Published

2021-03-30

How to Cite

Anysz, Hubert, et al. “Hybrid Predictions of the Homogenous properties’ Market Value With the Use of Ann”. Archives of Civil Engineering, vol. 67, no. 1, Mar. 2021, pp. 285-01, doi:10.24425/ace.2021.136474.

Issue

Vol. 67 No. 1 (2021)

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

Similar Articles

<< < 4 5 6 7 8 9 10 11 12 13 > >> 

You may also start an advanced similarity search for this article.