購屋者投資機率預測模型之探討

A Prediction Model for Housing Investment Probability

邱于修(Yu-Shiou Chiou) ； 周美伶(Mei-Ling Chou) ； 張金鶚(Chin-Oh Chang)

《臺大管理論叢》 23卷2期 (2013/06) Pp. 1-28

https://doi.org/10.6226/NTURM2013.JUN.R10018

摘要

本文採用「住宅需求動向調查」2006Q4至2007Q3之已購屋者問卷，以二元羅吉特模型之機率預測模型，分析投資者與自住者在住宅屬性、購屋搜尋行為與購屋者屬性之差異，並探討不同機率界限下，預測可信度最高之最適機率界限值。實證結果顯示，購買區位在中心都市、高單價、小面積產品、預售屋、中古屋與法／銀拍屋之購屋者，其為投資目的機率較高。此外，投資者具有搜尋時間短、年齡較長、男性、無固定職業及家庭平均月收入較高等特徵。本文運用貝氏定理得出當機率界限值為0.7時，模型預測可信度最高（投資者達72.22％，自住者達80.06％）。以2007Q4的資料作樣本外驗證，投資者預測可信度為65.52％，自住者預測可信度為84.51％。最後，模擬不同權重下，應貸而未貸以及違約與提前清償的誤差，對於金融機構個別可能造成的損失，模擬結果同樣顯示0.7為損失最少的機率界限值。

關鍵字

購屋行為 ； 購屋投資者 ； 預測機率模型

並列摘要

This study investigates the government-conducted ”Housing Demand Survey” from 2006Q4 to 2007Q3 to establish a binary logit model to analyze the housing attributes, search behaviors, and investors and owner-occupiers' personal characteristics for financial institutions prediction in determining house buyer motivation and reducing the loss incurred when payment is not advanced or is defaulted. The empirical results show that the locations, prices, sizes, and types of houses are the dominant factors affecting investment probability. Investors tend to select houses located downtown with high unit prices and small in size. They also tend to buy pre-sale, resold, and auction houses. The individual attributes of buyers, such as gender, age, occupation, and income, also play an important role in investment decisions. The proposed model has the highest prediction accuracy when the probability cutoff point is 0.7 and the investors' hit rate is 65.52 % in contrast to the owner-occupiers' 84.51%, as indicated by the out-sample test. This study also determines that financial institutions incur the least loss with a cutoff point of 0.7 under different weights, when payment is not advanced or is defaulted.

並列關鍵字

homebuyer's behavior ； housing investor ； probability prediction model

參考文獻

張梅音、鍾陳佳，2002，「住宅法拍屋屋屬性與拍定價格關係之研究─以台中市12 樓以下集合住宅為例」，土地問題研究季刊，1 卷2 期：頁12-20。(Chang, Mei-Ying, & Chung, Chen-Chia. 2002. The study on the relationship between attributes of residence in legal auction and the bid price. Land Issues Research Quarterly, 1 (2): 12-20.)

張金鶚、陳明吉、鄧筱蓉、楊智元，2009，「台北市房價泡沫知多少？─房價VS. 租金、 房價VS. 所得」，住宅學報，18 卷2 期：頁1-22。(Chang, Chin-Oh, Chen, Ming-Chi, Teng, Hsiao-Jung, & Yang, Chih-Yuan. 2009. Is there a housing bubble in Taipei? Housing price vs. rent and housing price vs. income. Journal of Housing Studies, 18 (2): 1-22.)

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：頁1-22。(Lin, Chu-Chia, & Ma, Yu-Chun. 2007. An application of mass appraisal and the hedonic equation in the real estate market in Taiwan. Journal of Housing Studies, 16 (2): 1-22.)

劉展宏、張金鶚，2001，「購屋貸款提前清償行為之研究」，住宅學報，10 卷1 期： 頁29-49。(Liu, Jan-Hong, & Chang, Chin-Oh. 2001. Mortgage borrowers’ prepayment behavior in Taiwan. Journal of Housing Studies, 10 (1): 29-49.)

郭敏華、郭迺鋒、邱耀初、范秉航，2005，「性別與投資行為：以台灣投票投資人為 例」，財務金融學刊，13 卷2 期：頁1-28。(Kuo, Min-Hua, Kuo, Nai-Fong, Chiu, Yao-Chu, & Fan, Ping-Hang. 2005. Gender and investment behavior: On Taiwanese individual investors. Journal of Financial Studies, 13 (2): 1-28.)