信用交易為企業最大的融資來源，為整體商業環境中最重要的一環，公司在產品銷售之後，客戶能否如期且全額付款，關係著公司整體的獲利能力。因此，本研究以某大半導體封裝大廠ABC公司之客戶為研究樣本,，來建構信用風險之評估模型，期望達到以下目的：
一、建立客戶信用核放之準則。
二、評估信用核放的未來潛在利益或損失，及預期違約機率。
三、改善收款作業及加速現金流入。
四、設立客戶信用異常預警機制。

本研究以該公司227家客戶為主要研究對象，主要研究構面有二：首先，由客戶之貢獻層面探討邊際貢獻率及客戶規模大小對可接受違約風險之影響。其次，由客戶之風險層面研究客戶延遲付款比率及客戶規模大小對違約事件之影響。綜合此二個構面計算出每一客戶之可接受違約風險及違約機率，藉由比較其風險及報酬，得出客戶信用評分，作為日後管理及評估客戶信用風險之依據。

本研究採用ABC公司內部銷售、獲利及應收帳款資料進行信用管理實證分析，採用的研究方法涵括會計及統計分析，包括現金流量信用決策模式、敘述性統計、多變量變異數分析、迴歸分析及羅吉斯迴歸等，茲將分析結果歸納如下：
一、不同可接受違約風險程度的客戶在邊際貢獻率、客戶營業規模大小有顯著的差異。
二、客戶的可接受違約風險程度與邊際貢獻率之間存在著正向的關係，邊際貢獻率愈高的客戶，其可接受違約風險程度愈大。
三、客戶的可接受違約風險程度與客戶規模大小之間存在著正向的關係，規模愈大的客戶其對公司營收貢獻愈大，相對的其可接受違約風險程度愈大。
四、不同違約事件的客戶在延遲付款比率及客戶規模大小有顯著的差異。
五、客戶違約事件的發生與客戶延遲付款比率之間存在著正向的關係，違約事件的發生集中在延遲付款比率較高之客戶。
六、客戶違約事件的發生與客戶規模大小之間存在著負向的關係，違約事件的發生集中在規模較小的客戶。

Business credit is the single largest source of business financing. It is an integral part of conducting business for most companies in today’s competitive business environment. In addition, a company’s profitability is tied up with whether the receivables can be collected on time and paid in full. Thus, to construct a credit risk assessment model, this research is based on a sampling of customers derived from ABC Inc, a provider of semiconductor packaging and testing services. This research attempts to achieve the following objectives:
a) Establish guidelines for determining whom the firm should grant credit to
b) Determine the probability of default and estimate potential future benefits or losses for credit granting
c) Improve collection activities and efforts to speed up cash inflow
d) Signal changing customer payment characteristics, terms-of-sale and credit- granting policies

Based on the research framework, 227 subjects were selected as the research population. There are two aspects in this research: first, on the customers’ contribution front, it explores how contribution margin ratio and size of account impact on acceptable default risk. Second, in the risk perspective, it examines the relationship between proportion of delayed payment, size of account and events of default. Finally, all customers’ credit scores can be obtained by means of comparing its acceptable default risk with probability of default in consideration of return-risk.

This research explores business practice in relation to credit management on the basis of internal information including sales, profit/loss and receivables data. The methods of research consist of accounting technique and statistic approaches, including NPV model of credit decision, descriptive statistics, analysis of variance, regression analysis and logistic regression analysis. The results of the research are summarized as follows:
a) There are significant differences in contribution margin ratio, and size of account among customers with different acceptable default risks.
b) There exists a positive relationship between contribution margin ratio and acceptable default risk. The higher the contribution margin, the greater acceptable default risk.
c) There exists a positive relationship between size of account and acceptable default risk. The bigger the size of account, the greater acceptable default risk.
d) There are significant differences in proportion of delayed payment, and size of account among customers with different events of default.
e) There exists a positive relationship between the proportion of delayed payment and the event of default. The events of default concentrate in the class of the highest proportion of overdue.
f) There exists a negative relationship between the size of account and the event of default. The events of default concentrate in the class of the smallest size of account.

1. Bandara, Ranjith and Clem Tisdell (2003), “Comparison of rural and urban attitudes to the conservation of Asian elephants in Sri Lanka: empirical evidence”, Biological Conservation, vol. 110, pp. 327-342.
2. Blakeley, Scott (2002), “Chapter 11s on the rise: red flags and steps to protect your credit sales”, Business Credit, NACM, New York, vol.104, pp.56-57.
3. Caouette, John B., Edward I. Altman and Paul Narayanan (1998), “Managing Credit Risk – The Next Great Financial Challenge”, John Wiley & Sons, Inc, pp.102-115.
4. Committee of Chief Risk Officers, (2002), “Credit risk management”, Credit Risk Management Working Group, vol. 4, pp.4.
5. Coyle, Brian (2000), “ Corporate credit analysis”, AMACOM Books, Chicago: New York, pp.23.
6. Coyle, Brian (2000), “ Measuring credit risk”, AMACOM Books, Chicago: New York, pp.2-53.
7. Coyle, Brian (2000), “Framework for credit risk management”, AMACOM Books, Chicago: New York, pp.1.
8. Doumpos, M., K. Kosmidou, G.. Baourakis and C. Zopounids (2002), “Credit risk assessment using a multicriteria hierarchical discrimination approach: A comparative analysis “, European Journal of Operational Research, Elsevier Science, pp.392.
9. Altman, Edward I. (1993), “Corporate Financial Distress and Bankruptcy: A Complete Guide to Predicting & Avoiding Distress and Profiting from Bankruptcy”, 2nd Edition, John Wiley & Sons, Inc, pp.187.
10. Elliehausen and Wolken (1993), “The demand for trade credit: An investigation of motives for trade credit use by small business”, Staff Study 165, Board of Governors of the Federal Reserve System, Washington.
11. Gujarati, Damodar N. (1999), “Essentials of econometrics”, 2nd edition, McGraw-Hill Higher Ed., pp. 449-450.
12. Hali, Martin (Feb 2003), “A/R outsourcing – coming of age in the new millennium”, Business Credit, NACM, New York, vol.105, pp.14-15.
13. Hampton, John J. (1989), “Financial decision making concepts, problems, and cases”, Prentice Hall, Englewood Cliffs, New Jersey, Fourth edition, pp.208-213.
14. Heilman, Carrie M. and Douglas Bowman (2002), “Segmenting consumers using multiple-category purchase data”, International Journal of Research, vol. 19, pp. 225-252.
15. Hosmer, David W. and Stanley Lemeshow (2000), “Applied logistic regression”, 2nd edition, John Wiley & Sons, Inc., pp.1-44.
16. Jordan, Ross and Westerfield (2003), “Fundamentals of corporate finance”, 6th edition, Mc Graw Hill, pp.275-724.
17. Kolari, James, Dennis Glennon, Hwan Shin and Michele Caputo (2002), “Predicting large US commercial bank failures”, Journal of Economics and Businesss, vol. 54, pp.361-387.
18. Lee, Tian-Shyug, Chih-Chou Chiu, Chi-Jie Lu and I-Fei Chen (2002), “Credit scoring using hybrid neural discriminant technique”, Expert Systems With Applications, pp. 245-254.
19. May, Elizabeth (1998), “Credit risk modeling: Design and application”, Glenlake Publishing Company Ltd., AMACOM, pp.59-60.
20. Molnar, Michele (2003), “Credit & collections: A global perspective “, Collections & Credit Risk, New York, pp.50-52.
21. Nielsen, Helena Skyt (1998), “Discrimination and detailed decomposition in a logit model”, Economics Letters, vol. 61, pp.115-120.
22. Pinches, George E. (1996), “Essentials of financial management”, 5th edition, Harper Collins College Publishers, pp.505-508.
23. Raspanti , Thomas M. and Eva Szakal (2002), “Creating value through credit risk mitigation”, Business Credit, NACM, New York, vol. 104, no 2, pp. 58-60.
24. Ricci, Cecilia Wagner (1999), “Receivables practices in American corporations”, Business Credit, NACM, New York, vol. 101, no4, pp. 32-35
25. Scherr, Frederick C. (1989), “Modern working capital management”, Prentice-Hall International, Inc., Englewood Cliffs, New Jersey, pp.156-237.
26. Schmidt, David (Dec 1996), “ The credit tug of war”, Controller Magazine.
27. Schuchardt, Michael (2003), “Receivables management: Moving beyond transactions”, Business Credit, New York, vol.105, pp.36-37.
28. Sloan, Frank A, Christopher J Conover and Dawn Provenzale (2000), “Hospital credentialing and quality of care “, Social science & medicine, vol. 50, pp.77-88.
29. Summers, Barbara and Nicholas Wilson (1996), “Trade credit management and the decision to use factoring: An empirical study”, Credit Management Research Group, Management Centre, University of Bradford, pp.1.
30. Wallis, Lyle (2001), “The Future of decisioning in the A/R process”, Business Credit, NACM, New York, vol. 103, no3, pp.50-60
31. Wallis, Lyle (2002), “Managing your receivables in today’s economy”, Strategic Finance Magazine, vol. 84, no 2, pp.42-45.
32. West, David (2000), “Neural network credit scoring models”, Computers & Operations Research, pp.1131-1132.
33. Wiley, Richard R. (1999), “Making credit history”, Industrial Distribution vol. 88, no 4, pp.112.