题名

不同人工神經網路架構在不動產大量估價之應用與比較

并列篇名

Complex Structures of Artificial Neural Network Comparison and Application on Real Estate Mass Appraisal

DOI

10.6677/JTLR.201205_15(1).0001

作者

沈育生(Yu-Sheng Shen);林秋瑾(Vickey Chiu-Chin Lin)

关键词

人工神經網路架構 ; 不動產大量估價 ; 多元迴歸 ; 分析多層函數連結網路 ; 倒傳遞網路 ; 輻狀基底函數網路 ; Real Estate Mass Appraisal ; Structures of Artificial Neural Network ; Back-Propagation Network ; Multilayer Functional-Link Network ; Radial Basis Function Network ; Multiple Regression Analysis

期刊名称

臺灣土地研究

卷期/出版年月

15卷1期(2012 / 05 / 01)

页次

1 - 29

内容语文

繁體中文

中文摘要

不動產價格的高低與土地徵收補償、土地開發的成本及收益、房地產投資等密切相關,因此,如何準確地估算不動產的價格一直是地政相關領域所關注之焦點。以往已有不少結合不動產大量估價與人工神經網路之研究,但所建構的模式大多以倒傳遞神經網路為主,甚少考量其他的網路模式,而且,其網路架構多採隨機指定,未能有系統地比較和分析不同網路架構的差異。因此,本研究透過不同的人工神經網路模式與多元迴歸來建構不動產估價的分析預測模式,並透過台北市006、007、008年不動產實際交易案例的實證分析,來比較多元迴歸與不同人工神經網路模式間之差異,以及進一步地比較人工神經網路中不同網路架構之優劣,以提供作為未來估價實務的參考之用。實證結果顯示,由倒傳遞神經網路(BPN)、輻狀基底函數網路(RBFN)、多層函數連結網路(MFLN)所建構的人工神網路模式,在模式適合度指標與模式預測度指標的表現上,皆遠優於多元迴歸模式,其中又以多層函數連結網路模式(MFLN)表現最佳,該模式的預測準確度除超過一般實務要求水準外,更優於以往研究所建構的人工神經網路模式。另外,在網路架構的分析比較上,顯示隱藏層與其單元數的數目愈多,會使模式趨於複雜,進而使模式收斂較慢;而在模式適合度與預測度的表現上,除倒傳遞神經網路模式(BPN)顯示二層隱藏層的模式表現較佳外,輻狀基底函數網路(RBFN)與多層函數連結網路(MFLN),皆顯示一層隱藏層之模式表現較佳。

英文摘要

Real estate prices affect the compensation of land acquisition, the cost and benefit of land development, and the investment of real estate. Thus, how to evaluate and predict the price of real estate precisely plays an important role in land economics research. This study uses both hedonic multiple regression method (MRA) and different artificial neural networks (ANN) to build models for evaluating and predicting on housing prices. We used the Year 2006 to 2008 data of housing transactions in Taipei City. The empirical results reveal that ANN can be a better alternative for predicting of housing prices. Among the different ANN housing prices models, the best predicting performance show at Multilayer Functional-Link Network (MFLN). In comparing network architecture, it indicates that more hidden layers and more attributes make the model more complicated and make the procedure converge slowly. In Back-Propagation Network (BPN), 2-layer model performs better than other network models in fitted-modeling and forecast accuracy, whereas it shows the performance of 1-layer model is better than 2-layer hidden model for both Multilayer Functional-Link Network (MFLN) and Radial Basis Function Network (RBFN).

主题分类 基礎與應用科學 > 永續發展研究
参考文献
  1. 林秋瑾、黃瓊瑩(2007)。特徵價格法之參數與半參數電腦輔助大量估價(CAMA)模型之研究─台北地區法拍屋住宅市場之實證分析。住宅學報,16(2),85-105。
    連結:
  2. 林秋瑾、楊宗憲、張金鶚(1996)。住宅價格指數之研究─以台北市為例。住宅學報,4,1-30。
    連結:
  3. 林祖嘉、林素菁(1993)。台灣地區環境品質與公共設施對房價與房租影響之分析。住宅學報,1,21-45。
    連結:
  4. 林祖嘉、洪得洋(1999)。台北市捷運系統與道路寬度對房屋價格影響之研究。住宅學報,8,47-67。
    連結:
  5. 林祖嘉、馬毓駿(2007)。特徵方程式大量估價法在臺灣不動產市場之應用。住宅學報,16(2),1-22。
    連結:
  6. 林素菁(2004)。台北市國中小明星學區邊際願意支付之估計。住宅學報,13(1),15-34。
    連結:
  7. 張怡文、江穎慧、張金鶚(2009)。分量迴歸在大量估價模型之應用─非典型住宅估價之改進。都市與計劃,36(3),281-304。
    連結:
  8. 陳奉瑤、楊依蓁(2007)。個別估價與大量估價之準確性分析。住宅學報,16(2),67-84。
    連結:
  9. 蔡瑞煌、高明志、張金鶚(1999)。類神經網路應用於房地產估價之研究。住宅學報,8,1-20。
    連結:
  10. 賴碧瑩(2007)。應用類神經網路於電腦輔助大量估價之研究。住宅學報,16(2),43-65。
    連結:
  11. 龔永香、江穎慧、張金鶚(2007)。客觀標準化不動產估價之可行性分析─市場比較法應用於大量估價。住宅學報,16(2),23-42。
    連結:
  12. Borst, R.A.(1992).Artificial Neural Networks: The Next Modelling/Calibration Technology for the Assessment Community.Property Tax Journal,10(1),69-94.
  13. Calhoun, A. C.(2001).Property Valuation Methods and Data in the United States.Housing Finance International,16,12-23.
  14. Din, A.,Hoesli, M.,Bender, A.(2001).Environmental Variables and Real Estate Prices.Urban Studies,38(11),1989-2000.
  15. DiPasquale, D.,Wheaton, C. W.(1996).Urban Economics and Real Estate Markets.New Jersey:Prentice Hall.
  16. Do, A.Q.,Grundnitski, G.(1993).A Neural Network Analysis of the Effect of the Age on Housing Values.Journal of Real Estate Research,8(2),253-264.
  17. Do, A.Q.,Grundnitski, G.(1992).A Neural Network Approach to Residential Property Appraisal.Real Estate Appraiser,58(3),38-45.
  18. Evans, A.,James, H.,Collins, A.(1992).Artificial Neural Network: An Application to Residential Valuation in the UK.Journal of Property Valuation and Investment,11,195-204.
  19. Goodman, A. C.,Thibodeau, T. G.(2003).Housing Market Segmentation and Hedonic Prediction Accuracy.Journal of Housing Economics,12(3),181-201.
  20. Guan, J.,Levitan, A.(2008).An Adaptive Neuro-Fuzzy Inference System Based Approach to Real Estate Property Assessment.Journal of Real Estate Research,30(4),395-421.
  21. International Association of Assessing Officers=IAAO(2010).Standard on Mass Appraisal of Real Property.USA:International Association of Assessing Officers.
  22. International Association of Assessing Officers=IAAO(2003).Standard on Automated Valuation Models (AVM).USA:International Association of Assessing Officers.
  23. Khalafallah, A.(2008).Neural Network Based Model for Predicting Housing Market Performance.Tsinghua Science and Technology,13(1),325-328.
  24. Kusan, H.,Aytekin, O.,Ozdemir, I.(2010).The Use of Fuzzy Logic in Predicting House Selling Price.Expert Systems with Applications,37(3),1808-1813.
  25. Limsombunchai, V.,Christopher, G.,Lee, M.(2004).House Price Predication: Hedonic Price Model vs. Artificial Neural Network.American Journal of Applied Science,1(3),193-201.
  26. Loans, D.(1990).The Variance in Valuations.London:Investment Property Databank.
  27. Matysiak, G.,Wang, P.(1995).Commercial Property Market Prices and Valuation: Analyzing the Correspondence.Journal of Property Research,12,181-202.
  28. McCluskey, W. J.,Adair, A.(1997).Computer Assisted Mass Appraisal: An International Review.England:Ashgate.
  29. McCluskey, W. J.,Borst, R. A.(1997).An Evaluation of MRA, Comparable Sales Analysis and ANNs for the Mass Appraisal of Residential Property in Northern Ireland.Assessment Journal,4(1),47-55.
  30. McGreal, S.,Adair, A.,McBurney, D.,Patterson, D.(1998).Neural Networks: The Prediction of Residential Values.Journal of Property Valuation and Investment,16(1),57-70.
  31. Michaels, R.G.,Smith, V. K.(1990).Market Segmentation and Valuing Amenities with Hedonic Models: The Case of Hazardous Waste Sites.Journal of Urban Economics,28,113-242.
  32. Muhammad, A. R.,Kuriakose, A.(2005).A Comparative Predictive Analysis of Neural Networks (Nns), Nonlinear Regression and Classification and Regression Tree (CART) Models.Expert Systems with Applications,29(1),65-74.
  33. Nelson, M.M,Illingworth, W. T.(1994).A Practical Guide to Neural Networks.Massachusetts:Addison-Wesley.
  34. Nguyen, N.,Cripps, A.(2001).Predicting Housing Value: A Comparison of Multiple Regression Analysis and Artificial Neural Network.Journal of Real Estate Research,22(3),313-336.
  35. Peterson, S.,Flanagan, A. B.(2009).Neural Network Hedonic Pricing Models in Mass Real Estate Appraisal.Journal of Real Estate Research,31(2),147-164.
  36. Selim, H.(2009).Determinants of House Prices in Turkey: Hedonic Regression Versus Artificial Neural Network.Expert Systems with Applications,36(2),2843-2852.
  37. Simpson, P. K.(1990).Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations.New York:Pergamon Press.
  38. Skapura, D. M.(1996).Building Neural Networks.New York:ACM Press.
  39. Tay, D.P.,Ho, D. K.(1991).Artificial Intelligence and the Mass Appraisal of Residential Apartments.Journal of Property Valuation and Investment,10(2),525-540.
  40. Wang, K.,Wolverton, M. L.(2002).Real Estate Valuation Theory.Boston:Kluwer Academic.
  41. Worzala, E.,Lenk, M.,Silva, A.(1995).An Exploration of Neural Networks and its Application to Real Estate Valuation.Journal of Real Estate Research,10(2),185-201.
  42. 李志祥(1995)。碩士論文(碩士論文)。淡江大學建築研究所。
  43. 李佳璋(2004)。碩士論文(碩士論文)。長榮大學土地管理與開發研究所。
  44. 李曉隆(2002)。碩士論文(碩士論文)。國立台灣科技大學企業管理研究所。
  45. 林明宏、張順孔、李德河、方世杰(2004)。類神經網路應用在阿里山公路崩壞潛能評估之研究。2004年全國災害危機處理學術研討會論文集
  46. 林英彥(2006)。不動產估價理論。臺北:文笙書局。
  47. 張金鶚(2003)。房地產投資與市場分析:理論與實務。臺北:華泰文化事業股份有限公司。
  48. 張斐章、張麗秋(2005)。類神經網路。臺北:東華書局。
  49. 葉怡成(2003)。應用類神經網路。臺北:儒林圖書公司。
  50. 魏如龍(2003)。碩士論文(碩士論文)。政治大學地政學系。
  51. 蘇文賢(2000)。碩士論文(碩士論文)。政治大學地政學系。
被引用次数
  1. 張金鶚,江穎慧,朱智揚(2019)。預售屋大量估價模型之建立。住宅學報,28(2),17-36。