基于机器学习的土地估值方法

doi:10.12341/jssms22392

系统科学与数学 ›› 2023, Vol. 43 ›› Issue (4): 841-857.DOI: 10.12341/jssms22392

• • 上一篇

基于机器学习的土地估值方法

周烨^{1, 2, 3}, 詹宝强⁴, 杨晓光^{1, 2}

1. 中国科学院数学与系统科学研究院, 北京 100190;
2. 中国科学院大学, 北京 100049;
3. 香港城市大学经济金融学院, 香港 999077;
4. 哈尔滨工业大学经济与管理学院, 哈尔滨 150000

收稿日期:2022-05-27 修回日期:2022-11-20 发布日期:2023-05-18
通讯作者: 杨晓光, Email:xgyang@iss.ac.cn
基金资助:
国家自然科学基金(72192800)资助课题.

PDF ( 29 ) 引用

周烨, 詹宝强, 杨晓光. 基于机器学习的土地估值方法[J]. 系统科学与数学, 2023, 43(4): 841-857.

ZHOU Ye, ZHAN Baoqiang, YANG Xiaoguang. Land Value Appraisal Based on Machine Learning[J]. Journal of Systems Science and Mathematical Sciences, 2023, 43(4): 841-857.

Land Value Appraisal Based on Machine Learning

ZHOU Ye^{1, 2, 3}, ZHAN Baoqiang⁴, YANG Xiaoguang^{1, 2}

1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190;
2. University of Chinese Academy of Sciences, Beijing 100049;
3. Department of Economics and Finance, City University of Hong Kong, Hong Kong 999077;
4. School of Management, Harbin Institute of Technology, Harbin 150000

Received:2022-05-27 Revised:2022-11-20 Published:2023-05-18

文章将基于互联网的区位信息和区域经济因素纳入土地评估,选取土地市场网“招拍挂”出让数据构建训练和测试样本,建立城市土地评估的回归、树、神经网络和深度学习四套模型,并对模型的预测能力和稳健性进行评价.研究表明, XGBoost 估值效果最优,适用于不同类型用地.此外, 文章发现土地基本属性、区位和宏观经济这三类因素均对土地估值有不可或缺的作用,其中监测地价和容积率上限的贡献度最大,说明宏观市场价格和可利用程度是最重要的影响因素.

关键词： 土地评估, 评估模型, 机器学习, 区位因素, 宏观经济因素

With the rapid increase of transaction volume in the land market and frequent usage of land as financial assets, traditional methodologies for determining land value are gradually unable to meet the needs of the current market due to their high cost and strong subjectivity. Therefore, cheap and efficient intelligent approaches are urgently needed. Based on previous literature, this paper takes land’s basic characteristics, business information nearby, and local macroeconomic information as the main pricing factors, and applies Linear Regression, Decision Tree, Artificial Neural Networks, and Deep Learning model to land evaluation. The data for training and testing the models is composed of 58, 815 parcels of land traded through bidding, auction, and listing, collected from Chinese websites in the period of January 2016 to June 2019. The study demonstrates that among those models, XGBoost outperforms all the other models and is well suited to different types of land. Furthermore, we measure the influence of enriched attributes on model performance and find that all three types of factors are indispensable for determining the price of land, especially the max floor area ratio and cities land prices, which means the macro-market value of the land and the degree of land availability are the most important factors.

Key words: Land appraisal, evaluation model, machine learning, location factors, macroeconomic factors

MR(2010)主题分类:

90B99
91B82

分享此文:

[1] 毛中根, 林哲. 土地储备制度与房地产开发——兼论地价与房价的关系. 上海经济研究, 2005, (8):58-63. (Mao Z G, Lin Z. Land reserving system and real estate development-Relation between land price and house price. Shanghai Economic Review, 2005, (8):58-63.)
[2] 卢新海, 黄善林, 冯广京. 不动产估价师培养与土地资源管理专业建设. 中国土地科学, 2006, 20(3):55-60. (Lu X H, Huang S L, Feng G J. Training of real estate appraisers and subject construction of land resource management. China Land Science, 2006, 20(3):55-60.)
[3] Vandell K D. Optimal comparable selection and weighting in real property valuation. Real Estate Economics, 1991, 19(2):213-239.
[4] Lisec A, Ferlan M, Lobnik F, et al. Modelling the rural land transaction procedure. Land Use Policy, 2008, 25(2):286-297.
[5] 龙开胜, 李敏. 长三角城市土地稀缺与土地利用效率的交互影响. 中国土地科学, 2018, 32(9):74-80. (Long K S, Li M. The interactive effect between urban land scarcity and land use efficiency in the Yangtze River Delta, China. China Land Science, 2018, 32(9):74-80.)
[6] 王雪峰. 垄断, 信息不对称及土地拍卖定价偏好的差异——以南昌市为例. 中国土地科学, 2018, 32(9):43-50. (Wang X F. Monopoly, information asymmetry and price preference difference of land auction in Nanchang city. China Land Science, 2018, 32(9):43-50.)
[7] Capozza D R, Israelsen R D, Thomson T A. Appraisal, agency and atypicality:Evidence from manufactured homes. Real Estate Economics, 2005, 33(3):509-537.
[8] Gau G W, Lai T Y, Wang K. Optimal comparable selection and weighting in real property valuation:An extension. Real Estate Economics, 1992, 20(1):107-123.
[9] Shimizu C, Karato K, Nishimura K. Nonlinearity of housing price structure:Assessment of three approaches to nonlinearity in the previously owned condominium market of Tokyo. International Journal of Housing Markets and Analysis, 2014, 7(4):459-488.
[10] 先倚懿, 金升平. 混合效应模型在新建住宅房价指数中的应用. 统计与决策, 2016, (15):87-90. (Xian Y Y, Jin S P. Application of mixed-effects model on new residential house price index. Statistic & Decision, 2006, (15):55-60.)
[11] 秦波, 孙亮. 容积率和出让方式对地价的影响——基于特征价格模型. 中国土地科学, 2010, 24(3):70-74. (Qin B, Sun L. The impacts of floor area ratio and transfer modes on land prices:Based on hedonic price model. China Land Science, 2010, 24(3):70-74.)
[12] Ahn J J, Byun H W, Oh K J, et al. Using ridge regression with genetic algorithm to enhance real estate appraisal forecasting. Expert Systems with Applications, 2012, 39(9):8369-8379.
[13] 申慧敏, 夏赞才, 刘婷, 等. MWTP计量模型研究与应用进展. 统计与决策, 2020, 36(23):37-41. (Shen H M, Xia Z C, Liu T, et al. Research and application advancements of MWTP measurement models. Statistic & Decision, 2020, 36(23):37-41.)
[14] Hu S G, Yang S F, Li W D, et al. Spatially non-stationary relationships between urban residential land price and impact factors in Wuhan city, China. Applied Geography, 2016, 68:48-56.
[15] You Q Z, Pang R, Cao L L, et al. Image-based appraisal of real estate properties. IEEE Transactions on Multimedia, 2017, 19(12):2751-2759.
[16] Afonso B, Melo L, Oliveira W, et al. Housing prices prediction with a deep learning and random forest ensemble. Anais do XVI Encontro Nacional de Inteligbência Artificial e Computacional. SBC, 2019, 389-400.
[17] Yuan F, Wei Y D, Xiao W Y. Land marketization, fiscal decentralization, and the dynamics of urban land prices in transitional China. Land Use Policy, 2019, 89:104208.
[18] Nichols J B, Oliner S D, Mulhall M R. Swings in commercial and residential land prices in the United States. Journal of Urban Economics, 2013, 73(1):57-76.
[19] Bao H X H, Glascock J L, Zhou S Z, et al. Land value determination in an emerging market:Empirical evidence from China. International Journal of Managerial Finance, 2014, 10(2):180- 199.
[20] 李志, 周生路, 张红富, 等. 基于GWR模型的南京市住宅地价影响因素及其边际价格作用研究. 中国土地科学, 2009, 23(10):20-25. (Li Z, Zhou S L, Zhang H F, et al. Exploring the factors impacting on the residential land price and measuring their marginal effects based on geographically weighted regression model:A case study of Nanjing. China Land Science, 2009, 23(10):20-25.)
[21] Cai H B, Henderson J V, Zhang Q H. China's land market auctions:Evidence of corruption?. The Rand Journal of Economics, 2013, 44(3):488-521.
[22] Qin Y, Zhu H J, Zhu R. Changes in the distribution of land prices in urban China during 2007- 2012. Regional Science and Urban Economics, 2016, 57:77-90.
[23] Cheshire P, Sheppard S. On the price of land and the value of amenities. Economica, 1995, 62:247-267.
[24] Chen Z C, Hu Y M, Zhang C J. An optimal rubrics-based approach to real estate appraisal. Sustainability, 2017, 9(6):909-927.
[25] Ferlan N, Bastic M, Psunder I. Influential factors on the market value of residential properties. Engineering Economics, 2017, 28(2):135-144.
[26] 沈昊婧, 冯长春, 侯懿珊. 城市间土地价格及影响因素的空间差异研究. 城市发展研究, 2014, 21(3):J0004-J0008. (Shen H J, Feng C C, Hou Y S. The study of spatial characteristics of urban land price and its influencing factors. Urban Development Research, 2014, 21(3):J0004-J0008.)
[27] Cockx K, Canters F. Incorporating spatial non-stationarity to improve dasymetric mapping of population. Applied Geography, 2015, 63:220-230.
[28] Du J, Peiser R B. Land supply, pricing and local governments' land hoarding in China. Regional Science and Urban Economics, 2014, 48:180-189.
[29] Huang Z H, Du X J. Strategic interaction in local governments' industrial land supply:Evidence from China. Urban Studies, 2017, 54(6):1328-1346.
[30] 张帅, 秦梦, 张少萍. 中国金融稳定性与土地价格动态关系研究. 金融发展研究, 2020, (8):20-27. (Zhang S, Qin M, Zhang S P. The dynamic relationship between financial stability and land price in China. Financial Development Research, 2020, (8):20-27.)
[31] Feldstein M. Inflation, tax rules, and the prices of land and gold. Journal of Public Economics, 1980, 14(3):309-317.
[32] 王伟, 谷伟哲, 翟俊, 等. 城市轨道交通对土地资源空间价值影响. 城市发展研究, 2014, 21(6):117-124. (Wang W, Gu W Z, Zhai J, et al. A study on the influence of rail transit on the spatial value of nearby land resources based on hedonic model. Urban Development Research, 2014, 21(6):117-124.)
[33] Melkumova L E, Shatskikh S Y. Comparing ridge and LASSO estimators for data analysis. Procedia Engineering, 2017, 201:746-755.
[34] Friedman J H. Greedy function approximation:A gradient boosting machine. Annals of Statistics, 2001, 29(5):1189-1232.
[35] Chen T, Guestrin C. Xgboost:A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016, 785-794.
[36] Ke G L, Meng Q, Finley T, et al. Lightgbm:A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 2017, 30:3149-3157.
[37] Prokhorenkova L, Gusev G, Vorobev A, et al. CatBoost:Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 2018, 31:6639-6649.

[1]	于翠翠, 寇红红, 孙少龙. 基于多语言搜索引擎数据预测旅游需求研究[J]. 系统科学与数学, 2022, 42(9): 2383-2398.
[2]	李莉, 季鹏成, 龚炜, 赵慧, 许佳, 于青云. 复杂系统近临界态分析与调控综述[J]. 系统科学与数学, 2022, 42(6): 1423-1437.
[3]	张金岱. 记忆性特征驱动的成品油价格预测研究[J]. 系统科学与数学, 2022, 42(5): 1300-1313.
[4]	龚谊承, 王晓杰, 邹一鸣. 基于蓄水池抽样的智能医保动态风险决策及应用[J]. 系统科学与数学, 2022, 42(4): 802-817.
[5]	阮腾飞, 张三国, 申立勇. 基于比例优势模型的有序数据分类[J]. 系统科学与数学, 2022, 42(10): 2817-2833.
[6]	朱章鹏，陈长波. 基于机器学习的柱形代数分解变元择序[J]. 系统科学与数学, 2020, 40(8): 1492-1506.
[7]	牟唯嫣，王春玲，赵昕. 基于空间填充准则的交叉验证方法及其应用[J]. 系统科学与数学, 2020, 40(2): 382-388.
[8]	黄志刚，刘佳进，林朝颖. 基于机器学习的上市公司财报舞弊识别前沿方法比较研究[J]. 系统科学与数学, 2020, 40(10): 1882-1900.

阅读次数

全文

摘要