應用類神經網路於電腦輔助大量估價之研究

Applying the Artificial Neural Network in Computer-assisted Mass Appraisal

10.6375/JHS.200712.0043

賴碧瑩(Peddy Pi-Ying Lai)

電腦輔助大量估價 ； 類神經網路 ； 特徵價格 ； 房價 ； computer assisted mass appraisal CAMA ； artificial neural network ANN ； back-propagation neural network BPN ； hedonic price ； property price

住宅學報

16卷2期（2007 / 12 / 01）

43 - 65

繁體中文

政府機關之不動產估價作業主要是提供課稅地價爲目的而衍生之行政工作，目前台灣主要以路線估價作業方式處理公部門地價，因此往往需要投入大量的人力、經費。此與歐美等國普遍應用的電腦輔助大量估價作業(computer assisted mass appraisal, CAMA)有極大差異。90年代初期，由於資訊產業的快速成長，利用電腦模擬人類思考模式，而發展出來的類神經網路(artificial neural network, ANN)演算方法被廣泛地運用於各種不同層面的研究。直到90年代後期才慢慢的被運用在不動產估價。 本研究將分別運用特徵價格及倒傳遞類神經網路預測高雄市不動產價格，試圖建立一套大量估價模型。經研究實證分析得知，在總體樣本數時，倒傳遞類神經網路預測較特徵價格法之預測能力較佳。但是如果將樣本區分爲90%樣本內及10%樣本外資料，特徵價格法之預測能力較佳，而這樣的實證結果說明，在運用各式估價模型時，可以進行交互驗證並且從中找出最適估價模型。

In early times, the land value assessments in Taiwan were made manually and wasted too much manpower, which was very different from the computer-assisted mass appraisal approach adopted in Western countries. In the early 1990's, due to the development of information technology, many researchers imitated the functioning of the human brain to develop the neural network and it was applied in different areas. In the late 1990s, the back-propagation neural network (BPN) was applied to real estate appraisal. This study applies the back-propagation neural network and hedonic price method to predict real estate prices in Kaohsiung city. We evaluate the model performance of the BPN and hedonic price in forecasting Kaohsiung's property prices. Two criteria are used, namely, the mean absolute percentage error (MAPE) and the forecasting error (FE). Regardless of which of the BPN approach or the hedonic price model is used, both are found to have similar forecasting power.

1. 蔡瑞煌、高志明、張金鶚(1998)。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：
2. Chen, C. L.,D. B. Kaber,P. G. Dempsey(2000).A New Approach to Applying Feed-Forward Neural Networks to the Predication of Musculoskeletal Disorder Risk.Applied Economics,3,269-282.
3. Din, A.,M. Hoesli,A. Bender(2001).Environmental Variables and Real Estate Prices.Urban Studies,38(11),1989-2000.
4. Do, A.Q.,G. Grundnistski(1993).A Neural Network Analysis of the Effect of the Age on Housing Values.Journal of Real Estate Research,8,252-264.
5. Do, A.Q.,G. Grundnitski(1992).A Neural Network Approach to Residential Property Appraisal.The Journal of Real Estate Research,58(3),38-45.
6. Evans, A.,H. James,A. Collins(1992).Artificial Neural Network: An Application to Residential Valuation in the UK.The Real Estate Research,58,38-45.
7. Hornik, K.,M. Stinchcombe,H. White(1989).Multilayer Feed Forward Networks are Universal Approximates.Neural Networks,2(5),359-366.
8. Hua, Gog Bee(1996).Residential Construction Demand Forecasting Using Economic Indicators: a Comparative Study Of Artificial Neural Network and Multiple Regression.Construction Management and Economics,14,25-34.
9. Markham, I. S.,T. R. Rates(1998).The Effect of Sample Size and Variability of Data on the Comparative Performance of Artificial Neural Networks and Regression.Computer Operation Research,25(4),251-263.
10. Masters, T.(1993).Practical Neural Network Recipes in C++.Boston:Academic Press.
11. McCluskey, W. J.,K. S. Dyson,Anand,D. Mcfall(1997).Computer Assisted Mass Appraisal.London:
12. McCluskey, W. J.,R. A. Borst(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.
13. McGreal, S.,A. Adair,D. McBurney,D. Patterson(1998).Neural Networks: the Prediction of Residential Values.Journal of Property Valuation & Investment,16(1),57-70.
14. Nguyen, N.,A. Cripps(2001).Predicting Housing Value: A Comparison of Multiple Regression Analysis and Artificial Neural Network.The Journal of Real Estate Research,22(3),313-336.
15. Palmquist, R. B.(1989).Land as a Different Factor of Production.Land Economics,65(1),23-28.
16. Rumelhart D. E.,G. E. Hinton,R. J. Williams,Rumelhart D. E.,J. L. McCleland (ed.)(1986)."Learning Internal Representation by Error Propagation," in Parallel Distributed Processing: Explorations in the Microstructure of Cognition.Cambridge:Massachusetts Institute of Technology Press.
17. Tay, D.P.,D.k. Ho(1991).Artificial Intelligence and the Mass Appraisal of Residential Apartments.Journal of Property Valuation & Investment,10,525-540.
18. Visit L.,G. Christopher,M. Lee(2004).House Price Predication: Hedonic Price Model vs. Artificial Neural Network.American Journal of Applied Science,3,193-201.
19. Wong, K.C.,A. P. So,Y. C. Hung,K. Wang,M. L. Wolvertom (ed.)(2001).Real Estate Valuation Theory.American Real Estate Society (ARES) Monograph.
20. Worzala E.,M. Lenk,A. Silva(1995).An Exploration of Neural Networks and its Application to Real Estate Valuation.Journal of Real Estate Research,10(2),185-201.
21. Zhang, G.,M.Y. Hu(1988).Neural Network Forcasting of the British Pound/ US Dollar Exchange Rate.Omega Int. Journal Magazine Science,26(4),495-506.
22. 李佳璋(2004)。碩士論文(碩士論文)。長榮大學。
23. 李曉隆(2002)。碩士論文(碩士論文)。國立台灣科技大學。
24. 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全國災害危機處理學術研討會論文集，台南:
25. 信義房屋(2004)。信義不動產論評論，8，15。
26. 高明志(1997)。碩士論文(碩士論文)。國立政治大學。
27. 張斐章、張麗秋、黃浩倫(2003)。類神經網路理論與實務。東華。
28. 陳韋龍(2004)。碩士論文(碩士論文)。中國文化大學。
29. 陳耀茂、殷純淵編著(2004)。類神經網路PCNeuron使用手冊。鼎茂。
30. 華昌宜、林秋瑾、賴碧瑩(2004)。財團法人台灣不動產資訊中心研究計畫。經建會。
31. 楊雅媛(2002)。碩士論文(碩士論文)。國立政治大學。
32. 葉怡成(2003)。應用類神經網路。儒林。
33. 魏如龍(2003)。碩士論文(碩士論文)。國立政治大學。

1. 林姿儀(2017)。應用腦波偵測於演化策略建立嫌犯辨識系統。淡江大學資訊管理學系碩士班學位論文。2017。1-88。 
2. 劉時旭(2012)。類神經網路應用於法拍不動產估價。中興大學土木工程學系所學位論文。2012。1-55。