The Mass Appraisal Study of Taxable Price of Commodity Housing Based on Automated Valuation Models

Kaiqing Wang; Yichao Wang; Zhuang Yang

doi:10.54097/3bf94c14

Authors

Kaiqing Wang
Yichao Wang
Zhuang Yang

DOI:

https://doi.org/10.54097/3bf94c14

Keywords:

Taxable price of commodity housing; automatic valuation models; random forest; rolling time window.

Abstract

The purpose of this study is to reveal the construction characteristics and advantages of the random forest automatic assessment model based on the transaction data of new commercial housing in X district of A city, and to introduce a rolling time window to enhance the model performance of random forest and guide its practice in the mass appraisal of taxable price of commodity housing. The methods of this study are GIS spatial information processing, random forest algorithm and rolling time window time series analysis. The research results show that: 1) the number of features in the feature subset at regression tree splitting and the node division rules at regression tree splitting have a large impact on the prediction accuracy of the random forest automatic assessment model. 2) The evaluation accuracy and generalization ability of the random forest automatic evaluation model are significantly better than those of the Hedonic model, with a goodness-of-fit of 98% and an average absolute error percentage of 2.7% in the training and test sets. 3) The introduction of a suitable rolling time window can improve the prediction accuracy and economic explanation ability of the random forest automatic valuation model. In conclusion, the random forest automatic valuation model based on rolling time windows can be widely used for automatic batch valuation of taxable prices of real estate in the study area.

Downloads

Download data is not yet available.

References

[1] Geng Xing. Assessment Issues in the Levying of Property Tax [J]. Taxation Research, 2004(04): 53-55. (in Chinese)

[2] Wang Xiuli, Li Hengkai, Liu Xiaosheng. GIS-Based Comparative Approach Model for Real Estate Market Valuation [J]. China Land Science, 2011, 25(10): 70-76, 97. (in Chinese)

[3] Geng Jijin. Urban Real Estate Mass Appraisal [M]. Beijing: China Financial Publishing House, 2012. (in Chinese)

[4] Sun Yuhuan. Construction of Hedonic Price Models Based on Massive Transaction Data [J]. Statistics and Decision, 2011(02): 9-13. (in Chinese)

[5] Zhu Chenming. Application of Hedonic Price Model in Mass Appraisal of Property Tax Bases [D]. Baoding: Hebei University, 2014. (in Chinese)

[6] Wang Rui. Construction of BP Neural Network Model for Real Estate Valuation [J]. Journal of Shandong Agricultural University (Natural Science Edition), 2016, 47(6). (in Chinese)

[7] Xiao Chenglian. Research on Mass Appraisal of Residential Tax Bases Using Grey Correlation-Based GA-BP Neural Network [D]. Ganzhou: Jiangxi University of Science and Technology, 2016. (in Chinese)

[8] Wang Azhong, Li Qian. Research on Mass Appraisal of Property Tax Bases Using Rough Set Neural Networks [J]. Journal of Fuzhou University (Philosophy and Social Sciences Edition), 2019, 33(5). (in Chinese)

[9] Chiarazzo V, Caggiani L, Marinelli M, et al. A Neural Network Based Model for Real Estate Price Estimation Considering Environmental Quality of Property Location [J]. Transportation Research Procedia, 2014, 3: 1-10.

[10] Song Zujie. Application of Support Vector Regression-Based Mass Appraisal Model for Second-Hand Housing [D]. Chongqing: Chongqing University, 2016. (in Chinese)

[11] 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 [J]. Expert Systems with Applications, 2012, 39(2): 1772-1778.

[12] Xu Ge, Zhang Ke. Real Estate Price Valuation Based on Random Forest Model [J]. Statistics and Decision, 2014, (17): 82-85. (in Chinese)

[13] Pang Feng. Application of Random Forest Model in Mass Appraisal of Second-Hand Housing [D]. Chongqing: Chongqing Jiaotong University, 2017. (in Chinese)

[14] Chen Shiqin, Wang Hongwei. Machine Learning-Based Mass Appraisal Model for Real Estate [J]. Statistics and Decision, 2020, 36(09): 26-30. (in Chinese)

[15] Breiman L, Friedman J H, Olshen R A, et al. Classification and Regression Trees [M]. Belmont: Wadsworth, 1984.

[16] Li Hang. Statistical Learning Methods [M]. Beijing: Tsinghua University Press, 2012. (in Chinese)

[17] Liu Yanli. A Review of Random Forest [D]. Tianjin: Nankai University, 2008. (in Chinese)

[18] Kok N, Koponen E, Martinez-Barbosa C A. Big Data in Real Estate? From Manual Appraisal to Automated Valuation [J]. The Journal of Portfolio Management, 2017, 43(6): 202-211.

[19] Calainho F D, Francke M K. A Machine Learning Approach to Price Indices: Applications in Commercial Real Estate [J]. The Journal of Real Estate Finance and Economics, 2022, 64: 1-28.

[20] Han Hui. Application of Hedonic Price Model in Mass Appraisal of Property Tax Bases [D]. Shijiazhuang: Hebei University of Economics and Business, 2014. (in Chinese)

[21] Bai Xue. Research on Mass Price Appraisal of Existing Housing in Nantong Based on Hedonic Price Model [D]. Hefei: Hefei University of Technology, 2015. (in Chinese)

[22] Del Giudice V, De Paola P, Forte F, et al. Real Estate Appraisals with Bayesian Approach and Markov Chain Hybrid Monte Carlo Method: An Application to a Central Urban Area of Naples [J]. Sustainability, 2017, 9(12): 1-15.