Homogeneous Feature Transfer and Heterogeneous Location Fine-Tuning for Cross-City Property Appraisal Framework

  • Yihan GuoEmail author
  • Shan Lin
  • Xiao Ma
  • Jay Bal
  • Chang-tsun Li
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 996)


Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model. As different cities usually contain a different set of location features (district names, apartment names), most existing mass appraisal methods have to train a new model from scratch for different cities or regions. As a result, these approaches require massive data collection for each city and the total training time for a multi-city property appraisal system will be extremely long. Besides, some small cities may not have enough data for training a robust appraisal model. To overcome these limitations, we develop a novel Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning (HFT+HLF) cross-city property appraisal framework. By transferring partial neural network learning from a source city and fine-tuning on the small amount of location information of a target city, our semi-supervised model can achieve similar or even superior performance compared to a fully supervised Artificial neural network (ANN) method.


Property valuation Transfer Learning Mass appraisal 


  1. 1.
    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)CrossRefGoogle Scholar
  2. 2.
    Arribas, I., García, F., Guijarro, F., Oliver, J., Tamošiūnienė, R.: Mass appraisal of residential real estate using multilevel modelling. Int. J. Strateg. Prop. Manag. 20, 77–87 (2016)CrossRefGoogle Scholar
  3. 3.
    Bahrammirzaee, A.: A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems. Neural Comput. Appl. 19, 1165–1195 (2010)CrossRefGoogle Scholar
  4. 4.
    Benjamin, J.D., Guttery, R.S., Sirmans, C.F.: Mass appraisal: an introduction to multiple regression analysis for real estate valuation. J. Real Estate Pract. Educ. 7, 65–77 (2004)Google Scholar
  5. 5.
    Born, W.L., Pyhrr, S.A.: Real estate valuation: the effect of market and property cycles. J. Real Estate Res. 9, 455–485 (1994)Google Scholar
  6. 6.
    Brown, K.H., Uyar, B.: A hierarchical linear model approach for assessing the effects of house and neighborhood characteristics on housing prices. J. Real Estate Educ. 7, 15–24 (2004)Google Scholar
  7. 7.
    Cervelló, R., García, F., Guijarro, F.: Ranking residential properties by a multicriteria single price model. J. Oper. Res. Soc. 62, 1941–1950 (2011)CrossRefGoogle Scholar
  8. 8.
    Chiarazzo, V., Caggiani, L., Marinelli, M., Ottomanelli, M.: A neural network based model for real estate price estimation considering environmental quality of property location. Transp. Res. Procedia 3, 810–817 (2014)CrossRefGoogle Scholar
  9. 9.
    Chopra, S., Thampy, T., Leahy, J., Caplin, A., LeCun, Y.: Discovering the hidden structure of house prices with a non-parametric latent manifold model. In: ACM International Conference on Knowledge Discovery and Data Mining (KDD) (2007)Google Scholar
  10. 10.
    D ’amato, M.: Comparing rough set theory with multiple regression analysis as automated valuation methodologies. Int. Real Estate Rev. 10, 42–65 (2007)Google Scholar
  11. 11.
    Del Giudice, V., De Paola, P., Forte, F.: Using genetic algorithms for real estate appraisals. Buildings 7, 31 (2017)CrossRefGoogle Scholar
  12. 12.
    Downes, T.A., Zabel, J.E.: The impact of school characteristics on house prices : Chicago 1987–1991. J. Urban Econ. 52, 1–25 (2002)CrossRefGoogle Scholar
  13. 13.
    Fan, G.Z., Ong, S.E., Koh, H.C.: Determinants of house price: a decision tree approach. Urban Stud. 43, 2301–2315 (2006)CrossRefGoogle Scholar
  14. 14.
    Farmer, M.C., Lipscomb, C.A.: Using quantile regression in hedonic analysis to reveal submarket competition. J. Real Estate Res. 32, 435–460 (2010)Google Scholar
  15. 15.
    Ferreira, E.J., Sirmans, G.S.: Ridge regression in real estate analysis. Appraisal J. 56, 311 (1988)Google Scholar
  16. 16.
    Fu, Y., Xiong, H., Ge, Y., Yao, Z., Zheng, Y., Zhou, Z.H.: Exploiting geographic dependencies for real estate appraisal: a mutual perspective of ranking and clustering. In: ACM International Conference on Knowledge Discovery and Data Mining (KDD) (2014)Google Scholar
  17. 17.
    Goldberg, D.E., Holland, J.H.: Genetic algorithms and machine learning. Mach. Learn. 3, 95–99 (1988). Scholar
  18. 18.
    Isakson, H.R.: Using multiple regression analysis in real estate appraisal. Appraisal J. 69, 424 (2001)Google Scholar
  19. 19.
    Kanojia, A., Khan, M.Y., Jadhav, U.: Valuation of residential properties by hedonic pricing method-a state of art. Int. J. Recent Adv. Eng. Technol. (IJRAET) (2016)Google Scholar
  20. 20.
    Kauko, T.: Residential property value and locational externalities: on the complementarity and substitutability of approaches. J. Prop. Invest. Financ. 21, 250–270 (2003)CrossRefGoogle Scholar
  21. 21.
    Kempa, O., Lasota, T., Telec, Z., Trawiński, B.: Investigation of bagging ensembles of genetic neural networks and fuzzy systems for real estate appraisal. In: Nguyen, N.T., Kim, C.-G., Janiak, A. (eds.) ACIIDS 2011. LNCS (LNAI), vol. 6592, pp. 323–332. Springer, Heidelberg (2011). Scholar
  22. 22.
    Kontrimas, V., Verikas, A.: The mass appraisal of the real estate by computational intelligence. Appl. Soft Comput. J. 11, 443–448 (2011)CrossRefGoogle Scholar
  23. 23.
    Mansfield, J.R., Lorenz, D.P.: Shaping the future: the impacts of evolving international accounting standards on valuation practice in the UK and Germany. Prop. Manag. 22, 289–303 (2004)Google Scholar
  24. 24.
    Mccluskey, W., Anand, S.: The application of intelligent hybrid techniques for the mass appraisal of residential properties. J. Prop. Invest. Financ. 17, 218–239 (1999)CrossRefGoogle Scholar
  25. 25.
    Musa, A.G., Daramola, O., Owoloko, A., Olugbara, O.: A neural-CBR system for real property valuation. J. Emerg. Trends Comput. Inf. Sci. 4, 611–622 (2013)Google Scholar
  26. 26.
    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
  27. 27.
    Nghiep, N., Al, C.: Predicting housing value: a comparison of multiple regression analysis and artificial neural networks. J. Real Estate Res. 22(3), 313–336 (2001)Google Scholar
  28. 28.
    Pagourtzi, E., Assimakopoulos, V., Hatzichristos, T., French, N.: Real estate appraisal: a review of valuation methods. J. Prop. Invest. Financ. 21, 383–401 (2003)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Yihan Guo
    • 1
    Email author
  • Shan Lin
    • 1
  • Xiao Ma
    • 1
  • Jay Bal
    • 1
  • Chang-tsun Li
    • 1
    • 2
  1. 1.University of WarwickCoventryUK
  2. 2.Charles Sturt UniversityWagga WaggaAustralia

Personalised recommendations