(Luận văn) applying logistic model to predict the probability of default for construction enterprises in vietnam from 2014 to 2016

MINISTRY OF EDUCATION AND TRAINING THE STATE BANK OF VIET NAM BANKING UNIVERSITY OF HO CHI MINH CITY lu an va n TRINH THANH DAT p ie gh tn to APPLYING LOGISTIC MODEL TO PREDICT THE nl w PROBABILITY OF DEFAULT FOR CONSTRUCTION d oa ENTERPRISES IN VIETNAM FROM 2014 TO 2016 an lu nf va GRADUATION THESIS oi lm ul MAJOR: FINANCE – BANKING CODE: 7340201 z at nh z m co l gm @ n va - an Lu HO CHI MINH CITY - 2018 ac th si MINISTRY OF EDUCATION AND TRAINING THE STATE BANK OF VIET NAM BANKING UNIVERSITY OF HO CHI MINH CITY lu an va n TRINH THANH DAT p ie gh tn to APPLYING LOGISTIC MODEL TO PREDICT THE nl w PROBABILITY OF DEFAULT FOR CONSTRUCTION d oa ENTERPRISES IN VIETNAM FROM 2014 TO 2016 an lu nf va GRADUATION THESIS oi lm ul MAJOR: FINANCE – BANKING CODE: 7340201 z at nh z M.S TRAN KIM LONG m co l gm @ INSTRUCTOR an Lu HO CHI MINH CITY - 2018 n va ac th si i THE AUTHOR'S DECLARATION Full name: Trinh Thanh Dat Student class: HQ02-GE01, faculty of Banking and Finance, Banking University of Ho Chi Minh city Student code: 030630141126 I declare that this thesis has been composed solely by myself and that it has not been submitted, in whole or in part, in any previous application for a degree Except where lu an states otherwise by reference or acknowledgment, the work presented is entirely my own n va Ho Chi Minh City, May 18, 2018 p ie gh tn to Author oa nl w d Trinh Thanh Dat oi lm ul nf va an lu z at nh z m co l gm @ an Lu n va ac th si ii THE AUTHOR'S ACKNOWLEDGEMENT First of all, I would like to thank all lecturers at Banking University of HCMC Your enthusiastic and devoted instruction helped me to improve my logical thinking ability and knowledge In addition, I would like to thank Mr Tran Kim Long who enthusiastically instructed and encouraged me to complete this graduation thesis However, due to limited knowledge and practical experience and limited research time, lu the study cannot avoid certain shortcomings The author wishes to receive the comments an of members in the committee to complete the thesis va n Ho Chi Minh City, May 18, 2018 tn to Author p ie gh d oa nl w oi lm ul nf va an lu Trinh Thanh Dat z at nh z m co l gm @ an Lu n va ac th si iii BANKING UNIVERSITY OF HO CHI MINH CITY VIETNAM High-Quality Program of Banking and Finance ABSTRACT Author DAT, Thanh TRINH Title Applying logistic model to predict the probability of default for construction enterprises in Vietnam from 2014 to 2016 lu an 2018 Language English n va Year to M.S LONG, Kim TRAN gh tn Instructor p ie In the current overall development of the economy, banking credit plays a very important role in the economy of every country in the world and is especially important for nl w countries with underdeveloped financial markets like Vietnam because it is a main source d oa of funding for businesses However, recently, excessive credit growth, resulting in an lu uncontrolled credit quality, has caused some consequences for the banking system such va as: high credit risk, declining profit, liquidity reduced The paper focuses on building a ul nf model estimating credit risk for construction firms in Vietnam from 2014 to 2016 Based oi lm on the results of the study, the paper provides not only an effective tool to predict the probability of default of construction companies but also comments and policy z at nh implications for commercial banks to improve the quality of credit and reduce credit risk in the future z @ m co l companies, Vietnam gm Key words: Credit risk, Logistic model, Basel II, Probability of default, Construction an Lu n va ac th si iv INDEX LIST OF ACRONYMS LIST OF TABLES AND FIGURES CHAPTER 1: INTRODUCTION lu an n va 1.1 Research background 1.2 Significance of research 1.3 Object and scope of the study 1.4 Research questions Research methods 1.6 Structure of the themes p ie gh tn to 1.5 w SUMMARY OF CHAPTER Credit risk (Default risk) d 2.1 oa nl CHAPTER 2: LITERATURE REVIEW AND THEORETICAL FOUNDATIONS an lu Definition 2.1.2 Measuring credit risk 2.2 oi lm ul nf va 2.1.1 Probability of default (PD) 10 Definition 10 2.2.2 Measuring PD 10 z at nh 2.2.1 z Some previous research on measuring PD 12 2.4 Model evaluation methods 22 m co l gm @ 2.3 Confusion matrix 22 2.4.2 Accuracy 23 2.4.3 Sensitivity 23 an Lu 2.4.1 n va ac th si v 2.4.4 Specificity 23 2.4.5 Precision 23 2.4.6 F1 score 24 2.5 ROC Curve 24 2.5.1 Definition and some overviews 24 2.5.2 ROC‟s construction 25 SUMMARY OF CHAPTER 26 lu an CHAPTER 3: MODEL ESTABLISHMENT 27 n va 3.1 General concept 27 tn to 3.2 Building model 27 gh Logistic model and Model selection 27 p ie 3.2.1 3.2.2 Collection and cleaning data 27 nl w Building models 32 3.2.4 Apply the models into estimating the PD in 2016 35 3.2.5 Choosing cutoff values 35 d oa 3.2.3 nf va an lu oi lm ul SUMMARY OF CHAPTER 36 CHAPTER 4: VALIDATING MODEL‟S PERFORMANCE AND EVALUATING z at nh RESULTS 37 Evaluation indicators 42 4.4 ROC Curve (Receiver operating characteristic curve) 43 4.5 The area under curve (AUC) 44 z 4.3 m co l gm @ SUMMARY OF CHAPTER 45 Final result 46 n va 5.1 an Lu CHAPTER 5: CONCLUSIONS 46 ac th si vi 5.2 Limitations 46 5.3 Recommendations 47 5.4 Future research direction 47 PREFERENCES 48 APPENDIX 1: LOGISTIC MODEL EXPLANATION 54 APPENDIX 2: CODES IN R 56 APPENDIX 3: PROBABILITY OF DEFAULT OF LOGIT MODEL 59 lu an APPENDIX 4: PROBABILITY OF DEFAULT OF PROBIT MODEL 60 n va APPENDIX 5: PROBABILITY OF DEFAULT OF C LOG-LOG MODEL 61 p ie gh tn to d oa nl w oi lm ul nf va an lu z at nh z m co l gm @ an Lu n va ac th si LIST OF ACRONYMS lu an n va Full meaning Area Under Curve Balance Sheet Compound Annual Growth Rate Credit Rating Agencies Exposure at Default Expected Loss Internal Ratings Based Approach Income Statement Loan Equivalency Factor Loss Given Default Probability of Default Return on Asset Return on Equity Receiver Operating Characteristic Curve Return on Sales Small and Medium-sized Enterprises Unexpected Loss p ie gh tn to Abbreviations AUC BS CAGR CRAs EAD EL IRB Approach IS LEF LGD PD ROA ROE ROC Curve ROS SMEs UL d oa nl w oi lm ul nf va an lu z at nh z m co l gm @ an Lu n va ac th si LIST OF TABLES AND FIGURES Page Figure 2.1 Relationship between Expected and Unexpected Loss Figure 2.2 The Standardized Probit, Logit and C-Log-Log Links 12 Table 2.1 List of Ratios Tested 13 Table 3.1 Number of observations and defaults per year 27 Figure 3.1 Distribution of financial ratios before handling outliers 29 lu Figure 3.2 Distribution of financial ratios after handling outliers 30 an Table 3.2 Financial ratios in six categories 33 n va Table 4.1 Descriptive statistical table 35 to gh tn Table 4.2 Correlation matrix 36 Table 4.3 Regression table of Logit model 37 ie p Table 4.4 Regression table of Probit model 38 nl w Table 4.5 Regression table of C log-log model 39 d oa Table 4.6 Matrix confusion for logit model at cutoff of 0.01 40 an lu Table 4.7 Matrix confusion for probit model at cutoff of 0.01 40 Table 4.8 Matrix confusion for C log-log model at cutoff of 0.01 40 va oi lm ul nf Figure 4.1 Receiver Operating Characteristic Curves of three models 42 z at nh z m co l gm @ an Lu n va ac th si 48 PREFERENCES Altman, E I (1968) Financial ratios, discriminant analysis and the prediction of corporate bankruptcy The Journal of Finance, 23(4), 589-609 doi: 10.2307/2978933 Basel Committee on Banking Supervision (BCBS) (2004), Basel II: International Convergence of Capital Measurement and Capital Standards: A Revised Framework Retrieved from http://www.bis.org/publ/bcbs107.htm (15 April lu 2018) an Research, 4(1), 71-111 doi: 10.2307/2490171 n va Beaven, W H (1966) Financial Ratios as Predictors of Failure Journal of Accounting tn to Bessis, J (2015) Risk Management in Banking (4th ed.) Chichester: John Wiley & Sons gh p ie Ltd CXL Institute (2017) How to Deal with Outliers in Your Data Retrieved from w d oa nl https://conversionxl.com/blog/outliers/ (18 May 2018) an lu Deakin, E B (1972) A Discriminant Analysis of Predictors of Business Failure Journal of Accounting Research, 10(1), 167-179 doi: 10.2307/2490225 nf va ul Engelmann, B., Rauhmeier, R (2011), The Basel II Risk Parameter Estimation, z at nh New York: Springer oi lm Validation, Stress – Testing with Applications Loan Risk Management (2nd ed.) Engelmann, B., Hayden, Evelyn., & Tasche, D (2003) Measuring the Discriminative z l gm pp 32 @ Power of Rating Systems Bundesbank Series Discussion Paper, No 2003(01), m co Finlay, S (2012) Credit Scoring, Response Modeling and Insurance Rating: A practical guide to forecasting customer behavior (2nd ed.) Basingstoke: Palgrave an Lu Macmillan n va ac th si 49 Griner, P F., Mayewski, R J., Mushlin, A I., & Greenland P (1981) Selection and interpretation of diagnostic tests and procedures Annals of Internal Medicine, 94, 555-600 Hand, D J., Henley, W E (1997) Statistical Classification Methods in Consumer Credit Scoring: A Review Journal of The Royal Statistical Society: Series A, 160(3), 523-542 Hayden, E (2002), Modelling an Accounting-Based Rating Model for Austrian Firms, lu unpublished PhD dissertation, University of Vienna an Investopedia (2017) (10 May va n 2018) tn to John, W C (2014) Research Design: Qualitative, Quantitative, and Mixed Methods gh p ie Approaches (4th ed.) SAGE Publications, Inc Langohr, H M., Langohr, P T (2015) The Rating Agencies and their Credit Ratings: w oa nl What They Are, How They Work and Why They Are Relevant (1st ed.) Chichester: d John Wiley & Sons Ltd lu va an Lau, A H L (1987) A Five-State Financial Distress Prediction Model Journal of ul nf Accounting Research, 25(1), 1987, 127-138 oi lm Martin, D (1977) Early warning of bank failure: A logit regression approach Journal of Banking & Finance, 1(3), 249-276 doi: 10.1016/0378-4266(77)90022-X z at nh Memić, D (2015) Assessing credit default using Logistic regression and multiple z discriminant analysis: Empirical evidence from Bosnia and Herzegovina @ m co l 10.7906/indecs.13.1.13 gm Interdisciplinary Description of Complex Systems, 13(1), 128-153 doi: Metz, C E (1978) Basic principles of ROC analysis Seminars in Nuclear Medicine, an Lu 8(4), 283-298 n va ac th si 50 Ming-Yu, L (2015) Choosing Logistics Regression’s Cutoff Value for Unbalanced Dataset Retrieved from (10 May 2018) Natasha, M (2017) Credit Scoring: Part – Credit Scorecard Modelling Methodology Retrieved from (18 May 2018) Nguyen, D T (2004) Phương pháp ước tính tổn thất tín dụng dựa hệ thống sở lu liệu đánh giá nội Ha Noi: Banking Institute Publisher an n va Ohlson, J A (1980) Financial Ratios and the Probabilistic Prediction of Bankruptcy tn to Journal of Accounting Research, 18(1), 109-131 doi: 10.2307/2490395 ie gh Pontius Jr, G P., Si, K (2014) The total operating characteristic to measure diagnostic p ability for multiple thresholds International Journal of Geographical Information Science, 28(3), 570-583 doi: 10.1080/13658816.2013.862623 nl w d oa Powers, D M W (2011) Evaluation: From Precision, Recall and F – Measure to ROC, lu Informedness, Markedness & Correlation Journal of Machine Learning Credit Risk, Comptroller’s Handbook (2017) Retrieved from ul nf Rating va an Technologies, 2(1), 37-63 oi lm (15 May 2018) G (2017) z at nh Rodríguez, Generalized Linear Models Retrieved from z (28 May 2018) gm @ Satchell, S., Xia, W (2007) Analytic Model of the ROC Curve: Applications to Credit l Rating Model Validation A volume in Quantitative Finance, 113-133 doi: m co 10.1016/B978-075068158-2.50011-1 an Lu Schuermann, T (March 2003) What we know about Loss-Given-Default? Federal n va Reserve Bank of New York paper ac th si 51 Servigny, N D., & Renault, O (2004) Measuring and managing credit risk New York: McGraw-Hill Sobehart, J R., Sean, C K (2004) Performance Evaluation for Credit Spread and Default Risk Model (2nd ed.) London: Risk Books Song, Y (2015) Decision tree methods: applications for classification and prediction Shanghai Arch Psychiatry, 27(2), 130-135 Doi: 10.11919/j.issn.1002- 0829.215044 lu an Standard & Poors (2006) Staples Inc Corporate Credit Rating Raised to 'BBB+' On n va Improved Credit Metrics Retrieved from (23 May 2018) ie gh tn to credit-research/Staples-Inc-Corporate-Credit-Rating-Raised-To-BBB-On- p Stehman, S V (1997) Selecting and interpreting measures of thematic classification accuracy Remote Sensing of Environment, 62(1), 77-89 doi: 10.1016/S0034- w d oa nl 4257(97)00083-7 lu Stephanou, C., Mendoza J C (2005, April 22) Credit Risk Measurement Under Basel va an II: An Overview and Implementation Issues for Developing Countries World ul nf Bank Policy Research Working Paper, pp 33 oi lm Swets, J A (1988) Measuring the Accuracy of Diagnostic Systems Science, New Series, 240(4857), 1285-1293 z at nh Swets, J A (1996) Signal Detection Theory and Roc Analysis in Psychology and Collected Papers Retrieved z Diagnostics from @ State Bank of Vietnam (2014) Overall m co The l analysis-in-psychology.> (08 May 2018) gm