- Home
- Finance & Accounting
- Credit scoring models

# Credit scoring models Essay Example

- Category:Finance & Accounting
- Document type:Math Problem
- Level:Masters
- Page:2
- Words:842

(Course Tittle)

**Executive summary**

This report gives a brief insight of credit scoring model for a commercial bank who targets listed companies in US stock exchange. The reports gives the credit score model developed using the data of 1990 and 2010 only and the comparison made of the two periods.

**Introduction**

In effort to discover more understanding of the loan delinquency and creditworthiness among the corporate borrowers, this report is going to try to develop credit-scoring model to help in estimating credit worthiness of corporations among US public listed companies. The main aim of this project is to reduce the number of non-performing loans of the newly instituted commercial banks (Kanwar 2005). Credit is the amount that is granted by the banks to those applicants who have requested credit from the bank. This amount granted should be paid at a given specified time and the interest accrued(Kanwar 2005). The proposed credit-scoring model will decide among the good and bad loans advanced by the bank to its applicants and evaluate the category of the risk associated with corporations by generating credit score (Hand & Henley 2007). The credit score will be generated using the available information from the S & P information, financial statements and credit bureau report. The general risk the money lending institutions having whenever they give credit is called credit risk. Credit risk is therefore the risk that the creditors would not repay the loan when the loan is due and this has an adverse effect on the revenue of commercial banks (Hand & Henley 2007).

Credit scoring models are used by banks to evaluate corporate loan applications and differentiate high-risk companies from low risk credit defaulters. This model will be used in credit approval process to evaluate loan application that is capable of enhancing credit processing.

**Variable selection**

Both financial and non-financial factors can be well used in developing credit-scoring model where financial ratios are being taken as independent variables. In developing CSMS, credit-scoring model for corporations are financial ratios that are calculated from the financial statements, Altman’s Z score credit History and credit rating of some given corporations.

Credit score is the independent variable for credit scoring model for the listed companies(Hand & Henley 2007). Credit score is the number that represents the creditworthiness of corporate borrowers and other financial institutions.

**Task1, Run a regression of Ln(S&P rating, numerical value) on the five firm characteristics, separately for 1990 data and 2010 data**.

**2010: Model Summary**

Adjusted R Square | Std. Error of the Estimate | |||

**2010: Variance Analysis**

Sum of Squares | Mean Square | |||||

Regression | ||||||

Residual | ||||||

**2010: Coefficient**

Unstandardized Coefficients | Standardized Coefficients | ||||||

Std. Error | |||||||

(Constant) | |||||||

working_capitalassets | |||||||

retained_earningsassets | |||||||

EBITAssets | |||||||

Book_equityLong_term_debt | |||||||

SalesAssets |

**1990: Model Summary**

Adjusted R Square | Std. Error of the Estimate | |||

**1990: Variance analysis**

Sum of Squares | Mean Square | |||||

Regression | ||||||

Residual | ||||||

**1990: Coefficient **

Unstandardized Coefficients | Standardized Coefficients | ||||||

Std. Error | |||||||

(Constant) | |||||||

working_capitalassets | |||||||

retained_earningsassets | |||||||

EBITAssets | |||||||

Book_equityLong_term_debt | |||||||

SalesAssets |

**Task2, Please compare the two credit scoring models as suggested by 1990 data and 2010 data**

**Credit Scoring**

Altman’s Z score

The Atman’s Z score formula is given by:

Z=1.2X1+ 1.4X2 + 3.3X3 + 0.6X4 +1.0X5

X1 = Working capital/ Total assets ratio

X2 = Retained earnings/ Total assets ratio

X3 = Earnings before interest and taxes/ Total assets ratio

X4 = Market value of equity/ Book value of long-term debt ratio

X5 = Sales/ Total assets ratio

Z=1.2X1+ 1.4X2 + 3.3X3 + 0.6X4 +1.0X5

Z = (1.2*-0.365) + (1.4*0.476) + (3.3*1.726) + (0.6*0.003) +(1*-0.096)

= -.438 +0. 664 +5.6958 +0.0018 – 0.096

Z = 5.8276

Z=1.2X1+ 1.4X2 + 3.3X3 + 0.6X4 +1.0X5

= (1.2*-0.424) + (1.4*1.033) + (3.3*1.692) + (0.6*0.005) + (1.0*-0.113)

=- 0.5088 +1.4462 +5.5836 +0.003 -0.113

Z Score Zone of Differentiation |
||

Safe” Zone | Low Default Risk | |

5.8276 < Z < 2.99 | “Grey” Zone | Medium Default Risk |

Grey” Zone | Medium Default |

The difference between the two models is the value of the five firm characteristics which result into different regression values hence different risk level and constants.

**Task 3: The list of these five firm characteristics is surely not exhaustive in terms of potential credit risk determinants. Could you think of other factors relevant for credit risk and explain why they are relevant?**

There are financial factors and non-financial factors.

Non-financial factors include age of the borrowers, marital status of the borrowers, education status of the borrowers, business size

Financial factors include, liquidity ratios, cash flow management ratio and profitability ratio

**Task4 [4] Now take the 2010 data, calculate the predicted rating value (Ln(S&P rating, numerical value)) based on your regression coefficients, i.e., Predicted value of Ln(S&P rating, numerical value) = intercept + coefficient of**

Z=1.2X1+ 1.4X2 + 3.3X3 + 0.6X4 +1.0X5

=

2.186 + (1.2*-0.365) + (1.4*0.476) + (3.3*1.726) + (0.6*0.003) +(1*-0.096)

=

2.186 -.438 + 0.664 +5.6958 +0.0018 – 0.096

The difference between the predicted value and actual value will be;

= 8.0136- 5.8276

Reference

Hand, D. J., & Henley, W. E. (2007). Statistical Classification Methods in Consumer Credit Scoring: A Review. *Journal of the Royal Statistical Society, 160*(3),

Kanwar, A. A. (2005). Risk Management for Banks. *Journal of Market Forces, 1*(1)