互聯網的發展與近年來數據平台受到公私部門重視，資訊的取得與流通變得便捷，中國房地產文化目前有別於台灣，尚無實價登錄機制且地域面積廣大，傳統估價模型可能無法直接應用，面對房地產背後眾多的影響因素，本研究將預測建模目標放在泡沫化尚不嚴重且較具有潛力的中國新一線城市杭州市，自新浪二手房網爬取杭州市房地產數據，並自國家統計局取得各地區行政支出數據，作為實證分析資料。結合自動程序爬蟲抓取數據、統計分析與機器學習方法，期望對中國房地產建立一混合非監督式與監督式學習之模型。 在分群結果之後建構模型採用之技術為C5.0、三層CHAID、五層CHAID與Neural Network，挑選出最適合的模型為使用混合模型後的C5.0決策樹方法，達到降低變數維度亦提升或達到相當的預測準確率的雙贏目標，模型中行政地區、面積、總樓層為最頻出現的重要變數。 另外透過集群分析於行政支出的應用，發現2016年度杭州市投入的行政支出集中於余杭區、蕭山區、濱江區，成為賣屋及購屋者的第二項決策標準。 / In recent years, with the growth of the Internet and the importance of data platform on public sector and private sector. Getting and sharing information are made easily. The culture of real estate in China is different from Taiwan. For instance, there is no actual house price registration system. Furthermore, traditional estimate model may not be directly applicable to China which has the vast geographical area of the mainland. There are many factors to influence house price model. This study focus on Hangzhou city. Because the burst of real estate bubbles is not serious as first-tier cities and it is one of new first-tier cities in China. The research data were crawler from Sina second-hand housing website and National Bureau of Statistics. By using auto web crawler skill, statistical analysis, and machine learning method to build a real estate model in China, which was combining unsupervised learning method with supervised learning method. After clustering Hangzhou second-hand housing data, this study used C5.0, three layers Chi-Square Automatic Interaction Detector(CHAID), five layers CHAID, and Neural Network(NN). The study goal are both reducing dimension and getting better forecast accuracy. Choosing clustering- C5.0 model as appropriate house price model to achieve win-win situation after comparing final result. Administrative region, area, and total floor are the top three high frequency influential factors. Applying Clustering Analysis to administrative expenses data in Hangzhou, the study found that the government resource focus on Yuhang, Xiaoshan, and Binjiang. It can be the second decision-making criterion for house sellers and house buyers.

近年來，社會經濟進步，對「不動產估價」之需求日益殷切，例如投資房地產、利用房地產來進行借貸行為等各項需要，在在皆得依靠不動產估價的技術，因此提升了社會上對不動產估價的重視。而在今日科技如此蓬勃發展的資訊時代，若能將不動產估價的技術與電腦的數位技術相互結合，藉由電腦的強大計算能力與快速的回應能力，相信必能提升不動產估價的技術及準確度。 　所以本研究致力於將不動產估價與電腦科技相結合，期望能提升不動產估價的準確度，除了利用其強大的計算能力之外，本研究更進一步地將不動產估價動作與地理資訊系統ＧＩＳ（Geographic Information System）相結合，利用ＧＩＳ強大的地理資料處理能力，希望能將不動產估價的技術提昇至更高的境界。 　本研究的研究過程為先對不動產估價之理論與方法進行研究，並尋找出不動產估價時的程序及其所需要考量的事項，在整理融會之後，再進一步地結合ＧＩＳ，以建構出一個以ＧＩＳ為基礎的不動產估價系統。且每當一估價個案完成，系統便自動將此筆估價個案之資料與結果回饋（輸入）給系統，成為一筆新增之買賣實例，如此一來，買賣實例資料庫將會愈來愈大，愈來愈完整，也將會使得系統的估價能力愈準確、可信度愈高。 因為在台灣不動產估價已經逐漸受到社會各界，例如銀行、租賃公司和房屋仲介公司等的重視，所以本研究企圖整理出各種常用估價模式及其所需的資料，並結合地理資訊系統（Geographic Information System，GIS）的技術，建構出一個以ＧＩＳ為基礎的泛用型不動產估價資訊系統之原型，期能藉此提高不動產估價行為的效率與精確度，並希望對ＧＩＳ的應用領域提供一個新的窗口，進而擴大ＧＩＳ的長遠發展。 / Recently, the need for appraisal of real estate is more and more important for people. When we invest the money in the real estate or use real estate to borrow money, we must depend on the technique for appraisal of real estate. Now, we are in the information world. If we can take advantage of the ability of the computer to appraise the real estate, it must be able to promote the technique and accuracy of appraisal in real estate. 　So in this thesis, it was applied to combine the appraisal in real estate and the ability of the computer and it hoped that it could increase the accuracy of appraisal. Besides the computing ability, this thesis wanted to combine the technique GIS (Geographic Information System) and the appraisal in the real estate. It wanted to take advantage of the processing ability in geographic data in GIS to higher the technique in appraising real restate. 　In this thesis, we attempt to arrange some general appraisal models and data the models need and to use the technique of GIS to design a prototype appraisal system. We hope that the system will be able to higher the efficiency and accuracy of appraisal in real estate. And we hope we will create a new way to take advantage of the ability of GIS.

Det finns idag en trend i viljan att investera i samhällsfastigheter, det vill säga fastigheter där olika typer av samhällsservice bedrivs. Fördelen med denna typ av investeringar är att ägarna kan teckna långa hyresavtal med kommuner, landsting och staten som hyresgäst, vilket ger säkra kassaflöden i och med låg vakansrisk. Investeringsmarknaden för samhällsfastigheter är relativt ny för privata aktörer då dessa fastigheter tidigare ägdes i princip uteslutande av kommun och landsting, men som idag av olika anledningar valt att sälja och istället hyra tillbaka fastigheten av specialiserade fastighetsägare.  Studien syftar till att identifiera de osäkerheter/risker som existerar vid investeringar i samt förvaltande av samhällsfastigheter och främst vårdfastigheter i Sverige. Genom att intervjua aktörer som deltagit i tre studerade transaktioner av vårdfastigheter från 2011 har en investeringskalkyl samt en känslighetsanalys utformats och legat till grund för de slutsatser som dragits. Att investera i samhällsfastigheter har visat sig vara en relativt stabil och säker investering, då de långa kontraktens driftnetton bidrar till att investeringen kan räknas hem redan under första kontraktstiden. Dock med antagande om att inga oväntade kostnader uppstår. De största riskerna som föreligger gällande dessa fastigheter är restvärdesrisk på grund av svår alternativanvändning för dessa hyresgästanpassade byggnader, teknisk risk då fastigheterna behöver upprätthålla standard och viktiga funktioner samt politisk/jurisdisk risk där förändring i demografi, miljölagar, regleringar och krav påverkar samhällsfastigheters utveckling. Företagen som investerar i samhällsfastigheter är vanligtvis inriktade på denna typ av investering, vilket genom ökad kompetens inom området bidrar till en bra och långsiktig relation med hyresgästerna. Vidare har de inblandade aktörer en tämligen homogen syn på ansvarsfördelningar, kontraktsuppbyggnad och så vidare. Dessutom visar den demografiska utvecklingen i landet på en stor efterfrågan på samhällsfastigheter i framtiden och framför allt på vård- och omsorgsboenden. / There is currently a trend in the willingness to invest in public property, i.e. properties where different types of community services are provided. The advantage of this type of investment is that owners can sign long leases with tenants such as municipalities, counties and the state, providing secure cash flows and low vacancy risk. The investment market for public properties is relatively new to private operators as these properties have previously been owned almost exclusively by the municipality and county. Today, for various reasons, the municipalities and counties have decided to sell their properties and rent them back from specialized property owners. The study aims to identify the uncertainties/risks that are associated with investment and management of public properties, with a special focus on care properties in Sweden. An investment calculation and a sensitivity analysis were made through studies of three care property transactions in 2011 and interviews with the participating actors. The calculation and analysis have been the basis for the conclusions drawn. Investing in public real estate has proven to be a relatively stable and safe investment. The net operating income of the long leases that contribute to the investment could be considered as being paid back during the first contract period, assuming that no unexpected costs arise. The main risks that exist in these properties is salvage value risk due to severe alternative use for these tenant adjusted buildings, technical risk as the properties need to maintain standard and essential functions and at last political/legal risk where changes in demography, environmental laws, regulations and requirements affect public property development. Companies that invest in public real estate are usually focused on this type of investment, which through enhanced capabilities in the area contributes to a good and long-term relationship with tenants. Furthermore, the players involved have a rather homogeneous view of delegation of responsibility, contract structure and so on. Moreover, the demographic development in the country shows a high demand for public buildings in the future and especially in nursing and care homes.