Estimation of the probability of default : Credit Rish
Download as PPTX, PDF4 likes1,509 views
The document discusses estimating credit risk and the probability of default using techniques such as logistic regression and linear discriminant analysis, emphasizing the importance of data cleaning. It outlines the factors contributing to credit risk, notably credit scores and various sources of risk, as well as presents findings on model performance with accuracy rates for logistic regression at 93.6% and discriminant analysis at 89.5%. The analysis concludes that significant time is spent on data cleaning and highlights the superiority of logistic regression when data is not normal.
Estimation of the probability of default : Credit Rish
- 1. Estimating the probability of default: Credit Risk Mohamed Arsalan Qadri Sarvesh Saurabh Mohit Ravi
- 2. Summary • Credit risk – The probability of default • Data Cleansing • Logistic Regression • Linear Discriminant Analysis • Comparison of the LR and LDA • Factor Analysis
- 3. Credit Risk What is it? • The risk of default on a debt that may arise from a borrower failing to make required payments. Impact on the lender? • Lost principal and interest, disruption to cash flows, and increased collection costs. How to estimate it? • Credit risk arises from the potential that a borrower or counterparty will fail to perform on an obligation
- 4. Sources of risk? • For most banks, loans are the largest and most obvious source of credit risk. • There are other sources of credit risk both on and off the balance sheet including letters of credit unfunded loan commitments, and lines of credit. • Other products, activities, and services that expose a bank to credit risk are credit derivatives, foreign exchange, and cash management services. Credit Risk
- 5. Credit Scoring vs Risk Estimation of risk? • The risk posed by the borrower is inversely proportional to the credit score. • A statistically derived numeric expression of a person's creditworthiness that is used by lenders to access the likelihood that a person will repay his or her debts. • A credit score is based on, among other things, a person's past credit history (300-850)
- 6. Credit Scoring • Consumers can typically keep their credit scores high by maintaining a long history of always paying their bills on time and not having too much debt. • A FICO score is the most widely used credit scoring system. • A credit score is primarily based on a credit report information typically sourced from credit bureaus.
- 8. Data Cleaning • Serious Delinquency in two years. (Make a Pi chart for this)
- 9. • Revolving Utilization Of Unsecured Lines Data Cleaning
- 11. • Number Of Time 30-59 Days Past Due Not Worse Data Cleaning
- 12. • Number Of Time 60-89 Days Past Due Not Worse Data Cleaning
- 13. • Number Of Times 90 Days Late Data Cleaning
- 14. • Monthly Income • Replaced with Mean Data Cleaning
- 15. Data Cleaning • Monthly Income • Ran Multiple Linear Regression on Missing Values
- 16. Data Cleaning • Monthly Income • The Histogram after running Multiple Linear Regression on Missing Values
- 17. Data Cleaning • Debt Ratio • We found that the Debt Ratio was extremely high in many cases. • Upon Closer inspection, we found out that high debt ratio was present for those records whose Monthly Income was unknown. • From this we inferred that the Debt Ratio could most probably be the Debt.
- 18. Data Cleaning • Debt Ratio • We replaced the high values of debt ratio by dividing it by the predicted values of the monthly income. • The new mean after replacement was 0.67
- 19. Data Cleaning • Number of Dependents
- 20. Data Modelling • Split the dataset into Training data (70%) and Test Data (30%). • Computed Co-relation Matrix among Independent variables. • The variables had very less Co-relation amongst themselves. • Ran Logistic Regression by using Stepwise selection. • Ran Linear Discriminant Analysis. • Compared both the models by measuring their accuracy of prediction. • Ran both models on significant Factors using Factor Analysis.
- 22. Logistic Regression • Ran Logistic Regression separately for each variable. • Computed the ROC curve for each variable and compared the AUC value.
- 23. Stepwise Selection • Overall Model was Significant. • All the variables were included in the model. • The model built on the Training data was tested on the Test data. • Probability of default > 0.7 was coded as 1, and Probability of default <0.7 was coded as 0.
- 24. Logistic Regression on Test Data Overall Accuracy = (41374+291)/(41374+291+175+2661) = 93.6 % True Positive Rate = TP / (TP+FN) = 9.85% True Negative Rate = TN / (TN+FP) = 99.5% Predicted Values Actual Values Confusion Matrix
- 25. ROC curve for Test Data • AUC Value = 0.8557
- 27. Discriminant Analysis Overall accuracy =(38134+1717)/Total =89.5 % True Positive Rate = TP / (TP+FN) = 58% True Negative Rate = TN / (TN+FP) = 91.7% Predicted Predicted 0 1 Actual 0 Actual 1 38134 3415 1235 1717 Serious Deliquen
- 28. Comparison of Models Linear Discriminant Analysis Overall accuracy =89.5 % Predicted Predicted 0 1 Actual 0 Actual 1 38134 3415 1235 1717 Serious Deliquen Logistic Regression Overall Accuracy = 93.6 %
- 30. Factor Analysis
- 31. Factor Analysis Factor Pattern Factor1 Factor2 Factor3 Factor4 NumberOfTimes90DaysLate 0.54684 0.28062 0.26286 -0.0429 Factor 1 NumberOfTime60_89DaysPastDueNot 0.50016 0.3943 0.37949 -0.0015 RevolvingUtilizationOfUnsecured 0.60945 0.24942 -0.1861 -0.0285 NumberOfOpenCreditLinesAndLoans -0.5203 0.5275 0.1922 0.15051 NumberRealEstateLoansOrLines -0.4698 0.61529 -0.0292 0.09694 Factor 2 NumberOfDependents_num 0.03058 0.46357 -0.6034 -0.008 Monthlyincome_debt -0.4298 0.5044 -0.09 -0.1628 NumberOfTime30_59DaysPastDueNot 0.40861 0.49901 0.31943 0.05977 Factor 3 age -0.4301 -0.1476 0.65733 -0.0396 Factor 4 DebtRatio 0.05584 -0.0712 -0.0331 0.97112
- 32. Conclusion • 80% time spent on Data cleaning • Logistic Regression gives better results when data is not normal as compared to LDA • Factors can be grouped for a logical understanding, with Debt Ratio and age explaining high variance.
- 33. Thank you
Editor's Notes
- #23: ROC curve measures how well your binary classifier is performing. It is comparing the rate at which the classifier is making correct prediction vs the rate at which the classifier is making wrong predictions. The diagonal line in the middle represents the classifier making random guess. Which means it is right 50% of the time and wrong the other 50% of the time. Here we have the ROC curve for Monthly income. From this ROC curve, we can calculate the area under this curve. In this case 0.8508. The higher the AUC value, the better is the model. On the right, we have the AUC values for all the variables. Monthly Income has the best AUC value of 0.8508. Most of the other variables fall below 0.7 and debt ratio does worse than 0.5