Machine Learning Models for Real Estate Appraisal Constructed Using Spline Trend Functions

  • Mateusz Jarosz
  • Marcin Kutrzyński
  • Tadeusz Lasota
  • Mateusz Piwowarczyk
  • Zbigniew Telec
  • Bogdan TrawińskiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12033)


The paper presents methods of modeling the real estate market using trend functions reflecting changes in real estate prices over time. Real estate transaction prices that are used to create data-driven valuation models must be updated in line with the trend of their change. The primary purpose of the first part of the study was to examine the extent to which splines are suitable for the trend function compared to polynomials of the degree from 1 to 6. In turn, the second part was to compare the performance of prediction models built on the basis of updated data with various trend functions: splines and polynomials. The experiments were conducted using real data on purchase and sale transactions of residential premises concluded in one of the Polish cities. Four machine learning algorithms implemented in the Python environment were used to generate property valuation models. Statistical analysis of the results was carried out using non-parametric Friedman and Wilcoxon tests. The study showed the usefulness of applying splines to model trend functions.


Prediction models Machine learning Real estate appraisal Trend functions Spline functions 


  1. 1.
    Lasota, T., Sawiłow, E., Trawiński, B., Roman, M., Marczuk, P., Popowicz, P.: A method for merging similar zones to improve intelligent models for real estate appraisal. In: Nguyen, N.T., Trawiński, B., Kosala, R. (eds.) ACIIDS 2015, Part I. LNCS (LNAI), vol. 9011, pp. 472–483. Springer, Cham (2015). Scholar
  2. 2.
    Lasota, T., et al.: Enhancing intelligent property valuation models by merging similar cadastral regions of a municipality. In: Núñez, M., Nguyen, N.T., Camacho, D., Trawiński, B. (eds.) ICCCI 2015, Part II. LNCS (LNAI), vol. 9330, pp. 566–577. Springer, Cham (2015). Scholar
  3. 3.
    Kontrimas, V., Verikas, A.: The mass appraisal of the real estate by computational intelligence. Appl. Soft Comput. 11(1), 443–448 (2011). Scholar
  4. 4.
    Zurada, J., Levitan, A.S., Guan, J.: A comparison of regression and artificial intelligence methods in a mass appraisal context. J. Real Estate Res. 33(3), 349–388 (2011)Google Scholar
  5. 5.
    Peterson, S., Flangan, A.B.: Neural network hedonic pricing models in mass real estate appraisal. J. Real Estate Res. 31(2), 147–164 (2009)Google Scholar
  6. 6.
    Narula, S.C., Wellington, J.F., Lewis, S.A.: Valuating residential real estate using parametric programming. Eur. J. Oper. Res. 217, 120–128 (2012)CrossRefGoogle Scholar
  7. 7.
    Antipov, E.A., Pokryshevskaya, E.B.: Mass appraisal of residential apartments: an application of Random forest for valuation and a CART-based approach for model diagnostics. Expert Syst. Appl. 39, 1772–1778 (2012). Scholar
  8. 8.
    D’Amato, M.: Comparing rough set theory with multiple regression analysis as automated valuation methodologies. Int. Real Estate Rev. 10(2), 42–65 (2007)Google Scholar
  9. 9.
    Kusan, H., Aytekin, O., Özdemir, I.: The use of fuzzy logic in predicting house selling price. Expert Syst. Appl. 37(3), 1808–1813 (2010). Scholar
  10. 10.
    Woźniak, M., Graña, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Inf. Fusion 16, 3–17 (2014). Scholar
  11. 11.
    Jȩdrzejowicz, J., Jȩdrzejowicz, P.: A family of GEP-induced ensemble classifiers. In: Nguyen, N.T., Kowalczyk, R., Chen, S.-M. (eds.) ICCCI 2009. LNCS (LNAI), vol. 5796, pp. 641–652. Springer, Heidelberg (2009). Scholar
  12. 12.
    Burduk, R., Baczyńska, P.: Dynamic ensemble selection using discriminant functions and normalization between class labels – approach to binary classification. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS (LNAI), vol. 9692, pp. 563–570. Springer, Cham (2016). Scholar
  13. 13.
    Kazienko, P., Lughofer, E., Trawiński, B.: Hybrid and ensemble methods in machine learning. J. Univ. Comput. Sci. 19(4), 457–461 (2013)Google Scholar
  14. 14.
    Fernández, A., López, V., José del Jesus, M., Herrera, F.: Revisiting evolutionary fuzzy systems: taxonomy, applications, new trends and challenges. Knowl.-Based Syst. 80, 109–121 (2015). Scholar
  15. 15.
    Lughofer, E., Cernuda, C., Kindermann, S., Pratama, M.: Generalized smart evolving fuzzy systems. Evol. Syst. 6(4), 269–292 (2015). Scholar
  16. 16.
    Lasota, T., Telec, Z., Trawiński, B., Trawiński, K.: A multi-agent system to assist with real estate appraisals using bagging ensembles. In: Nguyen, N.T., Kowalczyk, R., Chen, S.-M. (eds.) ICCCI 2009. LNCS (LNAI), vol. 5796, pp. 813–824. Springer, Heidelberg (2009). Scholar
  17. 17.
    Krzystanek, M., Lasota, T., Telec, Z., Trawiński, B.: Analysis of bagging ensembles of fuzzy models for premises valuation. In: Nguyen, N.T., Le, M.T., Świątek, J. (eds.) ACIIDS 2010. LNCS (LNAI), vol. 5991, pp. 330–339. Springer, Heidelberg (2010). Scholar
  18. 18.
    Lasota, T., Telec, Z., Trawiński, B., Trawiński, K.: Exploration of bagging ensembles comprising genetic fuzzy models to assist with real estate appraisals. In: Corchado, E., Yin, H. (eds.) IDEAL 2009. LNCS, vol. 5788, pp. 554–561. Springer, Heidelberg (2009). Scholar
  19. 19.
    Lasota, T., Telec, Z., Trawiński, G., Trawiński, B.: Empirical comparison of resampling methods using genetic fuzzy systems for a regression problem. In: Yin, H., Wang, W., Rayward-Smith, V. (eds.) IDEAL 2011. LNCS, vol. 6936, pp. 17–24. Springer, Heidelberg (2011). Scholar
  20. 20.
    Trawiński, B.: Evolutionary fuzzy system ensemble approach to model real estate market based on data stream exploration. J. Univ. Comput. Sci. 19(4), 539–562 (2013). Scholar
  21. 21.
    Lughofer, E., Trawiński, B., Trawiński, K., Kempa, O., Lasota, T.: On employing fuzzy modeling algorithms for the valuation of residential premises. Inf. Sci. 181, 5123–5142 (2011). Scholar
  22. 22.
    Meijering, E.: A chronology of interpolation: from ancient astronomy to modern signal and image processing. Proc. IEEE 90(3), 319–342 (2002). Scholar
  23. 23.
    Piegl, L., Tiller, W.: The NURBS Book. Springer, Heidelberg (1995). Scholar
  24. 24.
    Runge, C.: Über empirische Funktionen und die Interpolation zwischen äquidistanten Ordinaten. Zeitschrift für Mathematik und Physik 46, 224–243 (1901).
  25. 25.
    Dierckx, P.: Curve and Surface Fitting with Splines. Oxford University Press, Oxford (1993)zbMATHGoogle Scholar
  26. 26.
    de Boor, C.: A Practical Guide to Splines. Springer, New York (2001)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Applied InformaticsWrocław University of Science and TechnologyWrocławPoland
  2. 2.Wroclaw Institute of Spatial Information and Artificial IntelligenceWrocławPoland

Personalised recommendations