使用格局圖分析風水對房屋訂價之影響 The Influence of Fengshui on Pricing Using House Plan

Date
2016
Authors
吳祚禎
Wu, Tsuo-Chen
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
本論文探討房屋內部風水對於房屋開價的三個問題,第一,房屋內部風水對其訂價是否造成影響;第二,哪些風水因素影響開價最多;第三,當被視為較不好的房屋時,是否能提出格局上的修改建議。為了研究這些問題,我們選擇使用房屋的格局圖,因為從格局圖中可以看出房屋的整體配置。由於目前沒有與房屋格局相關的資料集,根據研究目的,我們從房仲網站收集了許多房屋的格局圖及其價格以利研究。在於探討房屋內部風水與房屋訂價的關係中,我們採用了多核學習及支持向量回歸的技術來探討這些問題。其中,核心技術為使用風水書中的知識, 從格局圖中計算新的影像特徵。實驗結果顯示房屋的內部風水對於房屋訂價有影響,其中,門的位置、房屋外型與房間流通性的特徵為高度相關的風水特徵。最後,我們提出方法用於診斷風水不好的房屋。
The thesis aims at studying three questions regarding the relationship between fengshui and house pricing. First, does the internal fengshui of a house has an effect on its pricing? Second, what are the most influential fengshui features to the price? Third, can we diagnose the fengshui problems of a house? In order to answer these questions, we use house plan because a house plan shows the whole interior structure of a house. We collect numerous house plans from real estate website and their prices to facilitate our research. We use multiple kernel learning and support vector regression to study the relationship between the internal fengshui of a house and its price. All of the features are designed based on fengshui and exracted from a house plan. We found that the internal fengshui of a house has an impact on pricing. In particular, door alignment, house shape, and the room connectivity have the most significant influence. Finally, we propose a method to diagnose a house, identifying the fengshui features that may lower the house price.
Description
Keywords
風水, 房屋格局圖, 房屋訂價, 多核學習, 支持向量回歸, fengshui, house plan, house pricing, multiple kernel learning, support vector regression
Citation
Collections