Traditional Approaches to Credit Risk Measurement 20 years of modeling history.

Slides:



Advertisements
Similar presentations
Credit risk measurement: Developments over the last 20 years R R R
Advertisements

Credit Risk: Individual Loan Risk Chapter 11
Part 4: CREDIT RISK: TRADITIONAL AND INNOVATIVE METHODS FOR MANAGING THE LENDING FUNCTION Chapter 10: The Traditional Approach to Business Lending:
Governor’s Housing Conference Creating & Financing New Business September 27, 2013.
Financial Management F OR A S MALL B USINESS. FINANCIAL MANAGEMENT 2 Welcome 1. Agenda 2. Ground Rules 3. Introductions.
ACCOUNTING DATA, BANKRUPTCY, AND RISK. Introduction  Earnings is not the only accounting number available to investors in the capital market  CAPM 
Bootstrapping and Financing the closely held company
Credit Risk Management Chapters 11 & 12. Credit Risk Management  uniqueness of FIs as asset transformers –What do we mean? –What type of risk do FIs.
The Basics of Risk Management
CHAPTER 16 Introduction to Credit Risk
CHAPTER 18: CAPITAL BUDGETING WITH LEVERAGE
CHAPTER 19 Estimating Parameter Values for Single Facilities.
Credit Scoring and Scorecard Lending LESE 306 Fall 2008.
CHAPTER FIFTEEN Lending Policies And Procedures The purpose of this chapter is to learn why sound lending policies are important to banks and other lenders.
Farm Management Chapter 19 Capital and the Use of Credit.
Credit Risk: Individual Loan Risk Chapter 11 © 2008 The McGraw-Hill Companies, Inc., All Rights Reserved. McGraw-Hill/Irwin Part C.
Consequences of Basel II for the individual SME company H.A. Rijken Vrije Universiteit, Amsterdam International Conference Small business banking and financing:
Lending Team Analysis AGEC Spring Factors to Consider Credit scores assessing the borrower’s existing credit history. Business plan and.
11-1 Chapter 11 Overview – Part A  This chapter discusses types of loans, and the analysis and measurement of credit risk on individual loans. This is.
Small Business Loans Kim Pope, Vice President, Regional Manager Business Banking Group.
ACCT: 742-Advanced Auditing
Copyright © 2002 by The McGraw-Hill Companies, Inc. All rights reserved.
1 Topic 4. Measuring Credit Risk (Individual Loan) 4.1Components of credit risk 4.2 Usefulness of credit risk measurement 4.3 The return of a loan 4.4.
Modelling Credit Risk Croatian Quants Day Vančo Balen
Assessment of default probability in conditions of cyclicality Totmyanina Ksenia Moscow, 2014.
1 The Basics of Capital Structure Decisions Corporate Finance Dr. A. DeMaskey.
Overview of Credit Risk Management practices in banksMarketing Report 1 st Half 2009 Overview of Credit Risk Management practices – The banking perspective.
CREDIT RISK MEASUREMENT Classes #14; Chap 11. Lecture Outline Purpose: Gain a basic understanding of credit risk. Specifically, how it is measured  Measuring.
© 2003 The McGraw-Hill Companies, Inc. All rights reserved. Credit and Inventory Management Chapter Twenty Prepared by Anne Inglis, Ryerson University.
Chapter 19 The Analysis of Credit Risk.
Mrs.Shefa El Sagga F&BMP110/2/ Problems with the VaR Approach   Bankers The first problem with VaR is that it does not give the precise.
Granting Loans.
©2007, The McGraw-Hill Companies, All Rights Reserved 20-1 McGraw-Hill/Irwin Chapter Twenty Managing Credit Risk on the Balance Sheet.
CH.10 CREDIT ANALYSIS AND DISTRESS PREDICTION
The Link between Default and Recovery Rates: Implications for Credit Risk Models and Procyclicality Edward I. Altman, Brooks Brady, Andrea Resti, and Andrea.
McGraw-Hill/Irwin ©2008 The McGraw-Hill Companies, All Rights Reserved Chapter Sixteen Lending Policies and Procedures.
Credit Risk. Possibility of loss from the failure of loan or debt instrument repayments. Change in the repayment capacity of borrowers or debt instruments.
20-0 Credit Policy Effects 20.3 Revenue Effects Delay in receiving cash from sale May be able to increase price May increase total sales Cost Effects –
Credit is the privilege of using someone else’s money for a period of time and is accepted as a substitute for cash Creditor is any person/ business that.
Zeta Services Inc. Supply Chain Application July, 2009.
Evan Picoult, Citigroup September, 2004 PAGE 1 INTEGRATED RISK MANAGEMENT PRESENTED TO:World Bank Finance Conference BY:Evan Picoult, Managing Director.
The Three C’s of Credit Objectives: – Students will be able to describe the “Three C’s of Credit (Capacity, character, and collateral) and factors used.
Alternative Method for Determining Industrial Bond Ratings
Chapter 5 Risk Analysis.
1 Banking Risks Management Chapter 8 Issues in Bank Management.
Artificial Neural Networks for Data Mining. Copyright © 2011 Pearson Education, Inc. Publishing as Prentice Hall 6-2 Learning Objectives Understand the.
Corporate Credit Scoring Models. 2 Scoring Systems Qualitative (Subjective) Univariate (Accounting/Market Measures) Multivariate (Accounting/Market Measures)
McGraw-Hill /Irwin Copyright © 2004 by The McGraw-Hill Companies, Inc. All rights reserved Chapter Twenty-one Managing Risk on the Balance Sheet.
CHAPTER 5 CREDIT RISK 1. Chapter Focus Distinguishing credit risk from market risk Credit policy and credit risk Credit risk assessment framework Inputs.
KMV Model.
Purposes Evaluation of loan applicant “Big” picture view Variety of information and sources to help in evaluation of applicant.
11-1 Chapter 11 Overview – Part A  This chapter discusses types of loans, and the analysis and measurement of credit risk on individual loans. This is.
Credit Scoring and Scorecard Lending
Traditional Approaches to Credit Risk Measurement
Credit Risk: Individual Loan Risk Chapter 11
BUSINESS FINANCE  As ABM students we don’t need to be a hyper-intellectual human being like Jimmy Neutron  We don’t agree with Jessie Jane’s Price.
Capital Regulations and Management Chapter 6
Traditional Approaches to Credit Risk Measurement
Predicting Financial Distress (The Z-Score Analysis) by Edward I
Measuring Actuarial Default Risk
CHAPTER FIFTEEN Lending Policies And Procedures
By: Kelsea,Carmin, and Carlos
Topic 3. Measuring Credit Risk (Individual Loan)
Underwriting for Small Business and Consumer Digital Lending
Risk Management in Banking
Credit risk analysis & debt capacity
Christopher Irwin Taipei October 17, 2001
Understanding Risk II Aswath Damodaran.
Credit Risk Bond rating agencies Bond rating categories
Credit Risk Management
Presentation transcript:

Traditional Approaches to Credit Risk Measurement 20 years of modeling history

2 Expert Systems – The 5 Cs Character – reputation, repayment history Capital – equity contribution, leverage. Capacity – Earnings volatility. Collateral – Seniority, market value & volatility of MV of collateral. Cycle – Economic conditions. – recession default rates >10%, : < 3% p.a. Altman & Saunders (2001) –Non-monotonic relationship between interest rates & excess returns. Stiglitz-Weiss adverse selection & risk shifting.

3 Problems with Expert Systems Consistency –Across borrower. “Good” customers are likely to be treated more leniently. “A rolling loan gathers no loss.” –Across expert loan officer. Loan review committees try to set standards, but still may vary. –Dispersion in accuracy across 43 loan officers evaluating 60 loans: accuracy rate ranged from Libby (1975), Libby, Trotman & Zimmer (1987). Subjectivity –What are the optimal weights to assign to each factor?

4 Artificial Neural Networks Computerized expert systems attempt to replicate the judgment of experts using computerized decision making models. Elmer & Borowski (1988): expert systems correctly predicted 60% of failures 7-18 months before bankruptcy, whereas credit scoring models only forecast between 33% - 48% of failures.

5 Disadvantages of Induction- Based Expert Systems The time and effort required to translate the human experts’ decision processes into a system of rules. The difficulty and costs associated with programming the decision algorithm and maintaining the system. The inflexibility of the expert system to adapt to changing conditions.

6 Artificial Neural Networks Address These Problems Simulates the human learning process. Can make “educated guesses” when data are incomplete or noisy. Can adapt to changing conditions by continuing the “learning” process. Can incorporate non-quantifiable, subjective information into decision.

7 How do Neural Networks Work? Figure 2.1 Inputs –Data inputs: company financial statements Weights –Relative importance assigned to each data input in determining the value of the hidden units. Hidden Units –Output variables that are joined together to produce decisions.

8

9 Disadvantages of Neural Networks Can get very large quickly. 10 inputs and 12 hidden units produces 4.46 x possible network configurations. Can be over-trained to a particular database. Lack of transparency. Cannot check decisions since intermediate steps are hidden and may not be duplicated.

10 Tests of Neural Networks To estimate external credit ratings: –Moody & Utans (1995): outperform linear regressions in classifying bond ratings. –Singleton & Surkan (1995): 73% accuracy in predicting bond ratings whereas only 57% accuracy for a credit scoring model. To estimate bankruptcy. -Kim & Scott (1991): for 190 Compustat firms: predicts 87% of bankruptcies in year of bankruptcy, 75%, 59%, 47% 1-year prior, 2-years prior, and 3-years prior

11 Rating Systems Oldest Loan Rating System – OCC 5-point system: four low quality & one hi quality. –Pass/Performing0% loan reserve –Other assets especially mentioned (OAEM) 0% –Substandard Assets 20% –Doubtful Assets 50% –Loss Assets 100%

12 Natl. Assoc. of Insurance Commissioners (NAIC) Ratings NAIC Rating Capital Reserve (life insurance) 1 AAA,AA,A 0.3% 2 BBB 1% 3 BB 4% 4 B 9% 5 < B 20% 6 Default 30%

13 Internal Ratings at Banks 60% of US BHCs have internal ratings on a 1-10 scale covering 96% of large & mid sized corporate loans, 71% of small corp. loans, and 54% of retail loans. Internal ratings based on PD (60% of systems) or PD and LGD (40%). Most often used for risk reports & loan pricing. Other uses shown in Figure 2.2. Will be used for BIS II.

14

15 Problems with Internal Ratings Must be validated using large amounts of data & subjective factors. If used for regulatory capital purposes, concerns about integrity of system – incentive to “shade” ratings. Ratings must be transparent – consistent and compatible. Ratings must be flexible and responsive to changing conditions.

16 Credit Scoring Models Linear Probability Model Logit Model Probit Model Discriminant Analysis Model 97% of banks use to approve credit card applications, 70% for small business lending, but only 8% of small banks (<$5 billion in assets) use for small business loans. Mester (1997).

17 Linear Discriminant Analysis – The Altman Z-Score Model Z-score (probability of default) is a function of: –Working capital/total assets ratio (1.2) –Retained earnings/assets (1.4) –EBIT/Assets ratio (3.3) –Market Value of Equity/Book Value of Debt (0.6) –Sales/Total Assets (1.0) –Critical Value: 1.81

18 Problems with Credit Scoring Assumes linearity. Based on historical accounting ratios, not market values (with exception of market to book ratio). –Not responsive to changing market conditions. –56% of the 33 banks that used credit scoring for credit card applications failed to predict loan quality problems. Mester (1998). Lack of grounding in economic theory.