臺灣博碩士論文加值系統

不動產是眾多金融投資工具之一，亦可作為理賠、融資、處分及課稅的依據，因此正確評估不動產價格是相當重要的。在一般的估價上，最常以市場比較法作為估價方法，但在傳統的市場比較法中，對於變數的選取、影響權重的設定，以及修正比例的決定，皆是根據個別估價師的主觀意識做修正，其公正性與合理性令人存疑。
估價在不動產市場扮演著一不可或缺的角色，精確的估價不僅可提供消費者正確及充分的掌握購屋資訊，亦可作為政府擬定政策方針的基礎。由於台灣不動產市場為一不完全市場，消費者在購屋的同時更因資訊的不健全而遭受不必要之損失，因此精確及流通的估價資訊為健全台灣不動產市場之首要要件。
由於估價技術尚未成熟，估價師所估之不動產價格常常無法使人信服。本研究以類神經網路、灰關聯分析及類神經模糊為基礎，將其原理應用於不動產估價上，試圖解決過去估價方法本身之缺失，並作為估價人員輔助之工具。本研究主要以灰關聯分析得出影響不動產價格的代表性因素，再以演化式類神經網路與類神經模糊及演化式類神經網路進行實證比較分析，所建立之架構可做為未來建立不動產估價系統之參考。

Real estate is one of the most useful financial instruments and can be applied to the purposes of the settlement of claims, financing, auction and taxing. To make most use of this financial tool requires appraising the assets accurately. In general, the comparative method of markets is a common approach for the evaluation of real estate. However, the selection of variables and related weights of this method relies on the assessor’s subjective judgment and the justice and rationality of results are disputed.

Appraisement plays a very important role in the real estate market. Appropriate appraisement can provide the consumers and investors sufficient trade information and also support the planning of the government real estate police. As the real estate market in Taiwan is not a perfect market, the consumers are prone to suffer loss due to the lack of correct appraisement information. As a result, the precision and circulation of the appraisement information is critical for the real estate market.

Without the assistance of sophisticated appraisement techniques, real estate appraiser’s results can not convince the consumers. This study integrated evolutional neural network, gray relational and neural-fuzzy analysis approaches to construct an intelligent system and provide an objective view for the appraiser. The gray relational analysis is applied to extract important variables which are the inputs for the neural network during the empirical test. The structure of prototype system built in this study will provide a reference and basis for the development of advance real estate appraisement system in the future.

目錄
中文摘要.……………………………………………………………Ⅰ
ABSTRACT.………………………………………………..…………Ⅱ
誌 謝.………………………………………………………..……Ⅲ
目錄.……………………………………………………....………Ⅳ
表目錄……………………………………………….………………Ⅵ
圖目錄……………………………………………….….…….……Ⅷ


第一章 緒論……..…………………………………….……… 1
第一節 研究動機………………………..…………….……… 1
第二節 研究目的……..…………………………...…..…… 2
第三節 研究限制………………………………………..……..3
第四節 研究架構………………………………………………..4
第二章 相關理論與文獻回顧……………………..….……….5
第一節 不動產估價方法……………..…………….………… 5
第二節 不動產價格影響因素分析………….………….………9
第三節 類神經網路應用於不動產領域….……..….……….14
第三章 研究方法……………….…….………………….……18
第一節 類神經網路概論……………..…………….…..……18
第二節 灰關聯分析……………………..……………..….…23
第三節 模糊邏輯與類神經網路………..…….………………29
小結…..……………………..……….……..………………..36
第四章 實證結果……..…….…………………………………39
第一節 資料處理…………………………………………….…39
第二節 本研究所使用之三種模型……………….…………40
第三節 類神經網路實證結果分析………….………………..43
第四節 灰關聯分析結果…………….………..……………..49
第五節 類神經模糊實證結果…….…………………………..59
小結……..…………………………………….…………………67
第五章 結論與後續建議………………………………………..69
參考文獻……………………..…………………………….…..72
中文文獻…………………………………….…………………72
英文文獻……………………………………….…………..…74
附錄A………………………………………….……….….…...78

參考文獻
中文文獻
1.井上洋，天笠美知夫原著，陳耀茂譯　(2002)，模糊理論，五南圖書出版公司。
2.李家豪（2000），KD技術指標之類神經模糊交易決策支援系統， 靜宜大學企業管理系碩士論文。
3.林左裕(2000)，不動產投資管理，智勝文化。
4.林英彥(2000)，「不動產估價」九版，文笙書局。
5.林祖嘉(1992)，台灣地區房租與房價關係之研究，台灣銀行季刊，第43-1期。
6.林秋墐(1997)，住宅價格之省思：1975~1995-理論與應用，正揚出版社。
7.林國民（1996），高雄市自有住宅特徵價格之研究，成功大學都市計劃研究所碩士論文。
8.秉昱科技編譯　(1998)，模糊邏輯與類神經模糊實例說明，儒林出版社。
9.夏郭賢、吳漢雄（1998），灰關聯分析之線性數序前處理，灰色系統學刊，第一卷，第一期，47-53頁。
10.高明志(1997)，類神經網路應用於房地產估價之研究，國立政治大學地政學系碩士論文葉怡成(2001)，應用類神經網路，儒林出版社
11.高瑋堅（2000），購屋者特性與房屋買賣價差關係之研究，崑山科技大學。
12.翁淑貞（1992），臺北市都會區空氣污染對住宅價格影響之研究，國立中興大學都研所碩士論文。
13.葉怡成(2003)，類神經網路模式應用與實作，儒林出版社。
14.張能政(2003)，不動產估價行為研究－行為理論之應用，國立台北大學地政學系碩士論文。
15.張金鶚、林秋瑾、楊宗憲（1995），台灣地區住宅價格指數之研究，經建會。
16.陳奉瑤、梁仁旭（1999），評定公告土地現值方法之研究，國立政治大學學報第七十八期。
17.陳韋龍(2003)，應用類神經網路建立台北市房價區位特性之研究，中國文化大學建築及都市計畫研究所碩士論文。
18.陳鴻洲(2002)，應用質化量化多準則評估方法於不動產估價之研究，朝陽科技大學建築及都市設計研究所碩士論文。
19.游淑惠（1994），類神經網路應用於國宅需求特性之研究，成功大學都市計劃研究所碩士論文。
20.溫坤禮，黃宜豊，張偉哲，張廷政，游美利，賴家瑞　(2003)，灰關聯模型方法與應用，高立圖書。
21.溫坤禮，黃宜豊，陳繁雄，李元秉，連志峰，賴家瑞　(2002)，灰預測原理與應用，全華科技圖書。
22.楊憶萱(1999)，模糊專家系統在不動產估價之應用，朝陽科技大學財務金融研究所碩士論文。
23.蔡瑞煌(1995)，類神經網路概論，三民書局。
24.蔡芬蓮(1997)，法拍屋價格影響因素之研究，政治大學地政研究所碩士論文。
25.盧靜怡(2001)，企業經營績效排名之預測-灰色關聯分析與類神經網路之應用，國立台灣科技大學資訊管理研究所碩士論文。
26.魏如龍(2003)，類神經網路於不動產價格預估效果之研究，國立政治大學地政研究所碩士論文。

英文文獻
1.Bobby A. Newsome, Joachim Zietz (1992) ,“Adjusting Comparable Sales Using Multiple Regression Analysis-The Need for Segmentation “,The Appraisal Journal, January pp129-135.
2.Borst, R.A and McCluskey (1996) “The Role of Artificial Neural Networks in the Mass Appraisal of Real Estate”, paper presented to the Third European Real Estate Society Conference, Belfast, June 26-28.
3.Borst, R.A. (1991) “Artificial Neural Networks: The Next Modeling/Calibration Technology for the Assessment Community?”, Property Tax Journal, IAAO, 10(1):69-94.
4.Borst, R.A.(1995) “Artificial neural networks in mass appraisal”, Journal of Property Tax Assessment &Administration, 1(2):5-15.
5.Delvin D. Hawley, John D. Johnson Dijjotam Raina (1990), “Artificial Neural Systems: A New Tool for Financial Decision-Making”, Financial Analysis Journal November-December pp63-72.
6.Do, A. Q. , and Grudnitski, Gary (1992), “A Neural Network Approach to Residential Property Appraisal”, The Real Estate Appraiser, December pp38-45.
7.Do, A.Q. and Grudnitiski, G. (1993), “A Neural Network Approach to Residential Property Appraisal”, The Real Estate Appraiser, Dec:38-45.
8.Donald G., Daniel J.,and Winkler T. (1991), “Location and Amenities in Determining Apartment Rents: An Integer Programming Approach”, Appraisal Journal ;Apr;59,2,pp266-275.
9.Elaine Worzala, Margarita Lenk, and Ana Silva(1995), “An Exploration of Neural Networks and Its Application to Real Estate Valuation”, The Journal of Real Estate Research Volume 10, Number 2.
10.Henry M.K. Mok., Patrick P. K. Chan., Yiu-Sun Cho., (1995), “A Hedonic Price Model for Private Properties in Hong Kong” ,Journal of Real Estate Finance and Economics, 10:pp.37-48
11.Kershaw Paul, and Rossini Peter (1999),”Using Neural Networks to Estimate Constant Quality House Price Indices”, Fifth Pacific-Rim Real Estate society Conference Kuala Lumpur, Malaysia, 26-30.
12.Kohonen, T.(1987), “Self-Learning Inference Rules by Dynamically Expanding Context,” IEEE First International Conference on Neural Network.
13.Lloyd T. Murphy 3 (1989),”Determining the Appropriate Equation in Multiple Regression Analysis”, Appraisal Journal ; Oct；57,4；498-517.
14.Lancaster, K (1996), “Anew approach to consumer theory “,The Journal of Political Economy, Vol.74(2),pp132-152.
15.Lewis, O.M., Ware,J.A. and Jenkins, D. H.(2001), “Identification of Residential Property Sub-Markets using Evolutionary and Neural and Computing Techniques”, Neural Com putting and Applications, Vol.10,No.2,pp108-119.
16.Mcgreal,S., Adair,A., Mcburney, D.and Patterson, D.(1998), “Neural Networks :the Prediction of Residential Values”, Journal of Property Valuation &Investment, Vol.16,No.1,pp57-70.
17.Meacham Allen (1988), “Applying Regression Analysis to Real Estate Appraisals”, The Real Estate Appraiser and Analyst, Summer pp23-27.
18.Nauck D. und Kruse R. (1997), “A Neural-Fuzzy Method to Learn Fuzzy Classification Rules from Data”, In: Fuzzy Sets and Systems, 89, 277-288.
19.Nghiep Nguyen, Al Cripps(2001), “Predicting Housing Value: A Comparison of Multiple Regression Analysis and Artificial Neural Networks”, The Journal of Real Estate Research; Nov/Dec；22,3；313-336.
20.Rosenblatt F. (1957), “The perceptron: A Probabilistic model for information storage and organization in the brain,” Psychological Review, vol. 65, pp. 386-408.
21.Rossini Peter (1998), “Improving the Results of Artificial Neural Network Models for Residential Valuation”, Fourth Annual Pacific-Rim Real Estate Society Conference Perth, Western Australia, 19-21 January pp1-18.
22.Rossini, P.A. Kershaw, P.J. and Kooymans, R.R. (1992), “Micro-Computer Based Real Estate Decision Making and Information Management - An Integrated Approach”, 2nd Australasian Real Estate Educators Conference Adelaide 1992.
23.Rossini Peter (2000), “Using Expert Systems and Artificial Interlligence For Real Estate Forecasting”, Sixth Annual Pacific-Rim Real Estate society Conference Sydency, Australia, 24-27 January,pp1-10.
24.Rossini, P.A., Kershaw, P.J. and Kooymans, R.R. (1993), “Direct Real Estate Analysis - The UPmarket™ Approach to Real Estate Decision Making”, Third Australasian Real Estate Educators Conference, Sydney, 1993.
25.Rossini P.A. (1997), “Application of Artificial Neural Networks to the Valuation of Residential Property”, 3rd Pacific Rim Real Estate Society Conference, New Zealand.
26.Rossini P.A.(1997b), “Artificial Neural Networks versus Multiple Regression in the Valuation of Residential Property Australian Land”, Economics Review, Vol 3 No 1 November 1997.
27.Rummelhart, D.E., Hinton, G.E., and Williams, R.J., (1986), “Learning representations by back-propagating errors”, Nature 323,533-536.
28.Von Altrock, C., B. Krause, and H.-J. Zimmermann. H.-J.（1992）, “Advanced Fuzzy Logic Control Technologies in Automotivr Applications,” In Proc. IEEE Int. Conf. On Fuzzy System, pp. 835-842
29.White, H.,. Hornik K. and Stinchcombe M. (1992),” Artificial Neural Network”, Blackwell Publishers.
30.Worzala, E.M. and Silva ,A.(1996), “High-tech Valuation: Should Artificial Neural Network Bypass the Human Valuer ?”, Appraisal Journal, January,pp89-109
31.Worzala, E.M. L, M. and Silva ,A.( 1995), “An Exploration of Neural Network and Its Application to Real Estate Valuation”, The Journal of Real Estate Research,Vol.10,No.2,pp.185-202