English  |  正體中文  |  简体中文  |  Items with full text/Total items : 43312/67235
Visitors : 2021185      Online Users : 2
RC Version 5.0 © Powered By DSPACE, MIT. Enhanced by NTU/NCHU Library IR team.

Please use this identifier to cite or link to this item: http://nchuir.lib.nchu.edu.tw/handle/309270000/155036

標題: 農會信用部授信評估因素之研究-以某農會為例
A Case of Study on Credit Assessment Factors for the Credit Department of Farmers’Associations
作者: 顏慶華
Yan, Ching-Hwa
Contributors: 楊育誠
Yu-Chen Yang
應用經濟學系所
關鍵字: 農會信用部;授信評估;Logistic迴歸模型
Credit department of Farmers’ Association;Credit evaluation;Logistic regression analysis
日期: 2013
Issue Date: 2013-11-21 11:31:22 (UTC+8)
Publisher: 應用經濟學系所
摘要: 本研究主要目的為探討農會信用部授信評估之影響因素,並以銀行授信風險評估5P原則為基礎,即借款人、借款用途、還款來源、債權保障與借戶展望等因素,來評估授信戶的信用與風險,以羅吉斯迴歸模型(Logistic Regression Analysis)做為本研究的統計分析方法。
研究資料以彰化縣某鄉農會土地貸款、房屋貸款及政策性農業專案貸款為研究範圍,以2010年1月至2012年12月底辦理之所有貸款案件,排除其中信用不良及資格不符者後,有51件逾期三個月以上,列入逾期放款範圍,其餘422件屬正常繳款者,共計有473件為樣本,利用羅吉斯迴歸(Logist-Regression)模型進行資料分析。本研究共有十六項變數,分別為會員資格、性別、年齡、學歷、婚姻、職業 、信用狀況、貸款情況、貸款用途、年收入、擔保品所有權、保證人、財產狀況、貸款金額、貸款成數、貸款利率等十六項。
實證結果顯示,該模型之整體正確率為97.9%。顯著影響授信評估因素的變數:在顯著水準10%下有八個變數呈現顯著相關,其中「貸款情況」、「貸款金額」、「貸款利率」等三個變數與逾期繳款機率呈現顯著正相關;「年齡」、「年收入」、「擔保品所有權」、「保證人」、「財產狀況」等五個變數與逾期繳款機率呈現顯著負相關。影響較不顯著的變數:包括「會員資格」、「性別」、「學歷」、「婚姻」、「職業」、「信用狀況」、「貸款用途」、「貸款成數」等八項變數。
本研究實證模型可提供農會做為授信評估時之參考依據,並能有效控制授信
品質,降低授信風險與損失。
The main purpose of this study is to explore the factors influencing credit evaluations in the credit department of Farmers’ Association; and base on the 5P principle of bank’s credit risk evaluation, such as people, purpose, payment, protection, and perspective, the borrower’s creditability and risk are evaluated. The Logistic Regression Analysis is adopted as the statistical analysis method for this study.
The scope of the research data includes land loans, housing loans, and loans of strategic agricultural projects by one of the Farmers’ Association in Changhwa County. With loans between January, 2010 and December, 2012, excluding bad credits and disqualifications, there are 51 loans which overdue for more than three months and are included in the range of overdue loans; the remaining 422 loans belong to normal repayments. Total sample size is 473 and the Logistic Regression is used for data analysis. There are sixteen variables in the study and they are respectively,membership, gender, age, education, marital status, occupation, credit status, loan status, loan purpose, annual income, collateral ownership, guarantor, property status, loan amount, loan-to-value, and interest rate.
The empirical results show that the overall accuracy of the model is 97.9%; the variables significantly influence the credit evaluation factors, under the significance level of 10%, there are eight variables that show significant correlations. Among them, the “loan status”, “loan amount”, and “interest rate” are significantly and positively correlated with the probability of overdue payment. The five variables of “age”, “annual income”, “property ownership”, “guarantor”, and “property status” are significantly and negatively correlated with the probability of overdue payment. The eight less significant variables are “embership”, “gender”, “education”, “marital status”, “occupation”, “credit status”, “loan purpose”, and “loan-to-value”.
The empirical model of this study can provide Farmers’ Association with references for credit evaluations and can effectively control credit quality, reduce credit risks and losses.
Appears in Collections:[依資料類型分類] 碩博士論文

Files in This Item:

File SizeFormat
index.html0KbHTML126View/Open


 


學術資源

著作權聲明

本網站為收錄中興大學學術著作及學術產出,已積極向著作權人取得全文授權,並盡力防止侵害著作權人之權益。如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員,將盡速為您處理。

本網站之數位內容為國立中興大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用。

聯絡網站維護人員:wyhuang@nchu.edu.tw,04-22840290 # 412。

DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU/NCHU Library IR team Copyright ©   - Feedback