企業信用評分模型一直是金融機構持續發展並改進的授信參考工具之一。本文採用業界廣泛使用的羅吉斯迴歸模型，以國內某銀行太陽能電廠授信戶建置信用評分模型。不同於一般企業信用評分模型多以財務變數建置模型，太陽能電廠授信戶所提供的財務變數參考性不高，故本研究採用審核太陽能電廠融資案件之評估要素作為解釋變數之篩選，實證結果可供未來核貸相關案件參考。

The corporate credit scoring model, that financial institutions have kept developing and improving, is one of the credit reference tools. This paper adopts the widely used Logistic regression model, and constructs a credit scoring model for solar power plant loans. However, different from the general corporate credit scoring model, the solar power plant loans usually cannot be evaluated by financial figures mainly. As a result, we choose other criteria while evaluating solar power plant loans as explanatory variables. This study could provide some information while examining this kind of loans afterwards.

1. 前言............................................................................................................................................1

2. 文獻回顧....................................................................................................................................3

2.1 企業授信風險評估方法簡述....................................................................................................3

2.2 建構信用評分模型與應用.......................................................................................................3

3. 研究方法....................................................................................................................................5

3.1 辨識度...................................................................................................................................5

3.2 解釋變數的轉換.....................................................................................................................7

3.3 解釋變數的篩選.....................................................................................................................8

3.4 羅吉斯迴歸............................................................................................................................9

4. 實證分析...................................................................................................................................11

4.1 違約定義...............................................................................................................................11

4.2 資料收集與期間....................................................................................................................11

4.3 變數說明..............................................................................................................................11

4.4 實證結果.............................................................................................................................15

5. 結論與建議..............................................................................................................................20

參考文獻........................................................................................................................................21

王明國 (2005),「製作中小企業信用評分卡」, 國立政治大學經營管理碩士學程碩士論文。
方 豪, 李彥賢, 與姜廷宜 (2017),「廠商融資對銀行信用風險之影響」，金融研訓院，兩岸金融季刊，第五卷第四期，60-64。
黃文彥 (2016),「採用層級分析法(AHP)提升信用評分模型品質之研究」, 國立交通大學經營研究所博士論文。
萬智傑 (2007),「台灣中小企業之財務危機預警模型、信用評等與巴塞爾協定資本計提」, 東吳大學企業管理碩士論文。
謝有隆 (2006),「信用評分模型的建置與驗證」, 國立政治大學經濟研究所碩士論文。
鍾經樊, 黃嘉龍, 黃博怡, 與謝有隆 (2006),「台灣地區企業信用評分系統的建置, 驗證和比較」，經濟論文，34(4)，541-590。
Ohlson J. M., (1980), “'Financial Ratios and the Probabilistic Prediction of Bankruptcy”, Journal of Accounting Research, 18(1), 109-131.
Rothstein, H. G., (1986), “The effects of time pressure on judgment in multiple cue probability learning”, Organizational Behavior and Human Decision Processes, 37(1), 83-92.