第五章 實證分析
第二節 建議
本研究以特徵價格為理論依據,建立住宅價格之預測模型,如根據特徵價格之 定義將其套用於住宅研究上,意即住宅價格之影響因素為住宅本身之屬性。但住宅 之影響因素不可單從住宅屬性探討,消費者於住宅消費時除考量住宅屬性外,另一 方面,亦會考量住宅之鄰里環境。而住宅價格影響因素除住宅本身所具備之屬性及 鄰里環境特徵外,尚包含總體層面之因素。而本研究僅探討住宅屬性及鄰里環境特 徵對於住宅價格之影響,因住宅消費者在選購住宅時,多數會挑選符合自身偏好之 住宅標的物,住宅屬性及鄰里環境特徵為住宅消費者於選購住宅標的物時會考慮之 項目。後續研究可針對總體層面影響因素進行預測,如住宅價格指數之預測,並與 其它方法進行比較。
由於 SVM 本身具備良好的預測條件,使其於社會科學研究上受到良好的肯定 及評價。而 SVM 在預測操作上只需做簡易的參數設定,而最佳參數之產生為 SVM 經由不斷的訓練後所尋得,雖最佳參數為 SVM 之核心且有利於預測正確率之提 升,但 SVM 所尋求之最佳參數屬黑箱作業,其並無法保證該參數為模型之最佳參 數,故後續研究可從如何尋求單一的最佳參數進行探討。
住宅價格預測之研究所使用之資料數據皆不一,SVM 應用於住宅價格之研究亦 是如此,資料之使用型態亦有多種運用方式,包含小樣本的預測,資料的隨機選 取,或龐大之資料數據預測。從部分文獻可得知資料數據之大小可能會直接影響 SVM 預測之精準度,如 Thissen et al. (2003)提及 SVM 於較大的樣本下是不可行的,
表示可能因資料數據之大小而影響正確率,且 Zhong et al. (2009)亦提及於較小的樣 本數下有著較好的預測能力,顯見資料數據之多寡對於預測正確率亦是一項重要之 探討因素。如在小樣本之情況下,可能產生較好的預測結果或較高的預測正確率。
另外 SVM 對於大樣本之預測可能產生較差的預測結果。故資料數據的多寡顯然對 於 SVM 之預測績效可能造成顯著的影響性,但目前對於此方面並無文獻說明 SVM 適切的資料數據大小,後續研究對此可進一步探討之。另外,住宅價格皆有高低,
但 SVM 對於少數極端值可能較不易預測,故如以 SVM 進行住宅價格預測可選取數 據分布較為集中的資料,以提高預測精準度。
SVM 包含分類及迴歸之預測型態,本研究僅以迴歸模式的 SVR 進行探討,並 與 OLS 進行比較。於分類之型態上,後續研究可將 SVC 與其他同屬分類之方法進
行比較及探討。而以 SVC 建立模型前需界定資料分類類別,分類數之多寡可能會影 響預測之正確率,因此後續研究可針對幾類之分類類別為適切的設定方式作更明確 之探討。
參考文獻
一、 中文部分
1. 張金鶚、范垂爐,1991,房地產真實交易價格之研究,住宅學報,1 期:75-97。
2. 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 期:21-45。
3. 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 期:1-30。
4. 林國民,1996,高雄市自有住宅特徵價格之研究,國立成功大學都市計畫研究 所碩士論文。
5. 洪得洋、林祖嘉,1999,台北市捷運系統與道路寬度對住宅價格影響之研究,
住宅學報,8 期:47-67。
6. 林元興、陳錦賜,2000,影響住宅價格各種因素之探討,住宅學報,1 期:33-48。
7. 林素菁,2002,台灣地區特徵性房價函數估計不一致性問題之探討,2002 年中 華民國住宅學會第十一屆年會論文集。
8. 李泓見、張金鶚、花敬群,2006,台北都會區不同住宅類型價差之研究,台灣 土地研究,9 卷 1 期:63-87。
9. 林祖嘉、馬毓駿,2007,特徵方程式大量估價法在台灣不動產市場之應用,住 宅學報,16 卷 2 期:1-22。
10. 陳樹衡、郭子文、棗闕庸,2007,以決策樹之迴歸樹建構住宅價格模型-台灣 地區之實證分析,住宅學報,16 卷 1 期:1-20。
11. 蔡爾逸,2012,應用支撐向量機(SVM)於都市不動產價格預測之研究,國立中 央大學營建管理研究所碩士論文。
二、英文部分
1. Adelman, I. and Griliches, Z. (1961), “ On an Index of Quality Change ”, Journal of the American Statistical Association, 56:535-546.
2. Case, K. E. and Mayer, C. J. (1996), “ Housing Price Dynamics within a Metropolitan Area ”, Regional Science and Urban Economics, 26(3-4):387-407.
3. Cai, Y. D. and Lin, X. J. (2002), “ Prediction of Protein Structure Classes by Support Vector Machines ”, Computer chemistry, 26:293-296.
4. Cortes, C. and Vapnik, V. (1995), “ Support Vector Networks ”, Machine Learning, 20(3):273-297.
5. Do, A. Q. and Grudnitski, G. (1993), “ A Neural Network Approach to Residential Property Appraisal ”, The real estate Appraiser, 58:38-45.
6. Crone, T. M. (1988), “ House Price and the Quality of Public School:What Are We Buying? ”, Business Review, Sep./ Oct:3-14.
7. Frew, J. and Jud, G. D. (2003), “ Estimating the Value of Apartment Buildings ”, Journal of Real Estate Research, 25(1):77-86.
8. Gu, J., Zhu, M. and Jiang, L. (2011), “ Housing Price Forecasting Based on Genetic Algorithm and Support Vector Machine ”, Expert System with Applications, 38:
3383-3386.
9. Haurin, D. R. and Brasington, D. (1996), “ School Quality and Real House Price:
Inter and Intra-Metropolitan Effect ”, Journal of Housing Economics, 5:315-368.
10. Hayes, K. and Taylor, L. (1996), “ Neighborhood School Characteristics:What Signals Quality to Homebuyers? ”, Economic Review, 4:2-9.
11. Hoshino, T. and Kuriyama, K. (2010), “ Measuring the Benefits of Neighborhood Park Amenities: Application and Comparison of Spatial Hedonic Approaches ”, Environmental and Resource Economics, 45(3):429-444.
12. Huang, C. L. and Wang, C. J. (2006), “ A GA-based feature selection and parameters optimization for support vector machines ”, Expert Systems with application, 31:
231-240.
13. Huh, S. and Kwal, S. J. (1997), “ The Choice of Functional Form and Variables in the Hedonic Price Model in Seoul ”, Urban Studies, 34(7):989-998.
14. Hsu, C. W., Chang, C. C. and Lin, C. J. (2003), “ A Practical Guide to Support Vector
Classification ”.
15. Hsu, C. W. and Lin, C. J. (2002), “ A Comparison of Methods for Multi-Class Support Vector Machines ”, IEEE Transactions on Neural Networks, 13(2), March.
16. Joke, L. (2000), “ The Value of Trees, Water and Open Space as Reflected by House Prices in the Netherland ”, Landscape and Urban Planning, 48:161-167.
17. Jozef, Z., Alan, S. L. and Jian, G. (2011), “ A Comparison of Regression and Artificial Intelligence Method in a Mass Appraisal ”, Journal of Real Estate Research, 33(3):349-387.
18. Jud, G. D. and Watts, J. M. (1981), “ School and Housing Values ”, Land Economics, 57(3):459-470.
19. Kohavi, R. and John, G. H. (1997), “ Wrapper for Feature Subset Selection ”,
Artificial Intelligence, 97(12):273-324.
20. Lancaster, K. J. (1966), “ A New Approach to Consumer Theory ”, Journal of Political Economy, 74(2):132-158.
21. Lin , T. and Liu, Y. (2010), “ A Risk Early Warning Model in Real Estate Market Based on Support Vector Machine ”, IEEE Computer Society, 2010 International Conference on Intelligent Computing and Cognitive Informatics:50-53.
22. McMillen, D. P. and McDonald, J. (2004), “ Reaction of Prices to a New Rapid Transit Line:Chicago’s 1983-1999 ”, Real Estate Economics, 32(3):463-486.
23. Nguyen, N. and Cripps A. (2001), “ Predicting Housing Value:A Comparison of Multiple Regression Analysis and Artificial Neural Networks ”, The Journal of Real Estate Research, 22(3):313-336.
24. Raymond, Y. C. Tse (2002), “ Neighborhood Effect in House Price:Towards a New Hedonic Model Approach ”, Urban Studies, 37(7):1165-1180.
25. Ridker, G. and Henning, J. A. (1967), “ The Determinants of Residential Property Values with Special Reference to Air Pollution ”, Review of Economics and Statistics, 49(2):246-257.
26. Rosen, S. (1974), “ Hedonic Price and Implicit Markets:Product Differentiation in Pure Competition ”, Journal of Political Economy, 82:34-55.
27. Sirmans G. S., Macpherson, D. A. and Zietz E. N.(2005), “ The Composition of Hedonic Pricing Models ”, Journal of Real Estate Literature, 13(1):3-43.
28. Tay, D. P. H. and Ho, D. K. H. (1992), “ Artificial Intelligence and the Mass
Appraisal of Residential Apartments ”, Journal of Property Valuation and Investment, 10(2):525-540.
29. Tay, F. E. H and Cao, L. (2001), “ Application of Support Vector Machines in Financial Time Series Forecasting ”, Omega, (29):309-317.
30. Thissen, U., Brakel, R. V., Weijer, A. P. D., Melssen, W. J., and Buydens, L. M. C.
(2003), “ Using Support Vector Machines for Time Series Prediction ”, Chemometrics and Intelligent, 69:35-49.
31. Vilius, K. and Antanas, V. (2011), “ The Mass Appraisal of the Real Estate by Computational Intelligence ”, Applied Soft Computing, 11(1):443-448.
32. Vapnik, V. N. (1995), “ Statistical Learning Theory ”, J Wiley, New York.
33. Xie, X. S. and Hu, G. (2007), “ A Comparison of Shanghai Housing Price Index Forecasting ”, IEEE Computer Society, Third International Conference on Natural Computation:221-225.
34. Zhong, Y., Zhou, C., Huang, L., Wang, Y. and Yang, B. (2009), “ Support Vector Regression for Prediction of Housing Values ”, IEEE Computer Society, International Conference on Computational Intelligence and Security:61-65.