We demonstrate, with a transition matrix, how real estate prices as well as "trigger events" can affect the likelihood of homeowners re-defaulting in loan modification programs.
The document discusses consumer credit risk modeling. It covers various statistical and machine learning methods used for credit scoring, including logistic regression, neural networks, and support vector machines (SVM). Logistic regression models the probability of default as a function of input variables and is commonly used. Neural networks can combine and transform input characteristics in non-linear ways but may take longer to train than other methods. The goal is to accurately predict consumer credit risk and default based on application information.
Predicting Credit Card Defaults using Machine Learning AlgorithmsSagar Tupkar
This is a project that I worked on as a Capstone for my Masters in Business Analytics program at the University of Cincinnati. In this project, I have performed an end-to-end data mining exercise including data cleaning, distribution analysis, exploratory data analysis, model building etc. to identify and predict Credit Card defaults using Customer's data on past payments and general profile. In the process for building Machine Learning models, I have fit and compared the performance of multiple models and algorithms like Logistic Regreesion, PCA, Classification tree, AdaBoost Classifier, ANN and LDA.
Predicting Delinquency-Give me some creditpragativbora
This document provides an analysis of credit data to predict financial distress. It explores 150,000 consumer records using variables like income, age, credit lines, loans, and payment history to develop classification models. Logistic regression and neural networks are implemented and evaluated. Data preprocessing addressed issues like missing values. The best model can help banks better assess loan risk and improve profitability by tailoring interest rates. Overall, traditional and advanced techniques are used to create a superior model for predicting customer defaults.
Credit risks are calculated based on the borrowers’ overall ability to repay. Our objective was to use optimization in order to create a tool that approves or rejects loans to borrowers. We also used optimization to establish how much interest rate/credit will be extended to borrowers who were approved for a loan.
The document discusses the development of a credit default prediction model called Def_Catch using machine learning algorithms. Def_Catch was trained on a dataset of 100,000 examples with 11 attributes related to borrowers' credit histories and demographics. Random forest achieved the highest accuracy of 93.14% at predicting which borrowers would default in the next 2 years, outperforming logistic regression, naive bayes, decision trees, and multi-layer perceptron models. The top predictors of default included credit utilization, age, number of late payments, debt ratio, and income. Def_Catch provides insights into borrower risk that are difficult to discern from raw data alone.
IRJET- Prediction of Credit Risks in Lending Bank LoansIRJET Journal
This document discusses machine learning models for predicting credit risk in bank loan applications. It begins with an introduction to credit risk assessment and types of loans. Then, it describes how machine learning can be used to more accurately evaluate borrowers' ability to repay loans based on important variables like borrower characteristics, loan details, and repayment status. The document proposes using artificial neural network and support vector machine models to classify borrowers as good or bad credit risks based on these variables. It evaluates the accuracy of support vector machines and boosted decision tree models for the task of credit risk prediction.
This document describes building models to predict credit card default payments. It retrieves credit card data from a public dataset containing details on customers' personal information, credit limits, payment histories and default statuses. The data is explored through visualizations to identify relationships between variables. Two classification models are built using KNN and decision tree algorithms. The decision tree model achieves a higher accuracy of 80% compared to KNN's 74% accuracy, indicating decision trees are more suitable for predicting default payments from this credit card data.
The document discusses consumer credit risk modeling. It covers various statistical and machine learning methods used for credit scoring, including logistic regression, neural networks, and support vector machines (SVM). Logistic regression models the probability of default as a function of input variables and is commonly used. Neural networks can combine and transform input characteristics in non-linear ways but may take longer to train than other methods. The goal is to accurately predict consumer credit risk and default based on application information.
Predicting Credit Card Defaults using Machine Learning AlgorithmsSagar Tupkar
This is a project that I worked on as a Capstone for my Masters in Business Analytics program at the University of Cincinnati. In this project, I have performed an end-to-end data mining exercise including data cleaning, distribution analysis, exploratory data analysis, model building etc. to identify and predict Credit Card defaults using Customer's data on past payments and general profile. In the process for building Machine Learning models, I have fit and compared the performance of multiple models and algorithms like Logistic Regreesion, PCA, Classification tree, AdaBoost Classifier, ANN and LDA.
Predicting Delinquency-Give me some creditpragativbora
This document provides an analysis of credit data to predict financial distress. It explores 150,000 consumer records using variables like income, age, credit lines, loans, and payment history to develop classification models. Logistic regression and neural networks are implemented and evaluated. Data preprocessing addressed issues like missing values. The best model can help banks better assess loan risk and improve profitability by tailoring interest rates. Overall, traditional and advanced techniques are used to create a superior model for predicting customer defaults.
Credit risks are calculated based on the borrowers’ overall ability to repay. Our objective was to use optimization in order to create a tool that approves or rejects loans to borrowers. We also used optimization to establish how much interest rate/credit will be extended to borrowers who were approved for a loan.
The document discusses the development of a credit default prediction model called Def_Catch using machine learning algorithms. Def_Catch was trained on a dataset of 100,000 examples with 11 attributes related to borrowers' credit histories and demographics. Random forest achieved the highest accuracy of 93.14% at predicting which borrowers would default in the next 2 years, outperforming logistic regression, naive bayes, decision trees, and multi-layer perceptron models. The top predictors of default included credit utilization, age, number of late payments, debt ratio, and income. Def_Catch provides insights into borrower risk that are difficult to discern from raw data alone.
IRJET- Prediction of Credit Risks in Lending Bank LoansIRJET Journal
This document discusses machine learning models for predicting credit risk in bank loan applications. It begins with an introduction to credit risk assessment and types of loans. Then, it describes how machine learning can be used to more accurately evaluate borrowers' ability to repay loans based on important variables like borrower characteristics, loan details, and repayment status. The document proposes using artificial neural network and support vector machine models to classify borrowers as good or bad credit risks based on these variables. It evaluates the accuracy of support vector machines and boosted decision tree models for the task of credit risk prediction.
This document describes building models to predict credit card default payments. It retrieves credit card data from a public dataset containing details on customers' personal information, credit limits, payment histories and default statuses. The data is explored through visualizations to identify relationships between variables. Two classification models are built using KNN and decision tree algorithms. The decision tree model achieves a higher accuracy of 80% compared to KNN's 74% accuracy, indicating decision trees are more suitable for predicting default payments from this credit card data.
Factors Factors Influencing Credit Risk For Small And Medium Enterprise Loans...paperpublications3
Abstract: There has been an increased concern over high credit risk for small and medium enterprise loan in financial institutions. High interest rates, credit rating, recovery mechanisms and business experience play an important role in influencing credit risk for small and medium enterprise loans. The main objective of this study was to investigate factors influencing credit risk for small and medium enterprise loans a survey of banks in Kitale Town, Kenya. The specific objectives of the study were: To establish the influence of interest rates on credit risk of small and medium enterprise loans in banks, bto find out the influence of credit rating in credit risk of small and medium enterprise loans in banks, to establish the influence of recovery mechanism in credit risk of small and medium enterprise loans in banks, and to assess the influence of business experience in credit risk of small and medium enterprise loans in banks. Credit management theory, trade-off theory, modern portfolio theory were used to underpin the study. Explanatory research design was used in this study. The study targeted 331 employees from 11 Commercial Banks in Kitale. The study used stratified sampling technique. Interest rates, credit rating, recovery mechanism and business experience were taken as the independent variables while credit risk was the dependent variable. Pilot study was used to test the validity and reliability of the research instrument. Interest rates showed a positive and significant effect on credit risk (β= 0.153, ρ<0.05).><0.05).><0.05).><0.05). In conclusion, the study has established that whenever there are high short-term interest rates, there is an increase in credit risk. In addition, interest rate shifts are heterogeneous across the firm and have different implications for leverage and default in the short run than in the longer run. Hence the study recommends for need for a comprehensive risk management process that ensures the timely identification, measurement, monitoring, and control of risk.
Machine Learning Project - Default credit card clients Vatsal N Shah
- The model we built here will use all possible factors to predict data on customers to find who are defaulters and non‐defaulters next month.
- The goal is to find the whether the clients are able to pay their next month credit amount.
- Identify some potential customers for the bank who can settle their credit balance.
- To determine if their customers could make the credit card payments on‐time.
- Default is the failure to pay interest or principal on a loan or credit card payment.
Real options analysis (ROA) has several advantages over traditional decision making techniques for valuation and investment decisions under uncertainty. [1] ROA accounts for flexibility to modify decisions as new information arises, rather than viewing decisions as binary choices. [2] It uses stochastic processes and only considers favorable outcomes, avoiding the need to heavily discount cash flows or select a discount rate. [3] ROA thus treats uncertainty as a profit opportunity rather than something to avoid or overcorrect for.
This document describes a project using logistic regression to model credit risk. The student built three logistic regression models using different independent variables from a dataset of 29092 loan applications. Model 3, using loan amount, interest rate, grade of employment, employment length, annual income, age, and home ownership, had the lowest AIC score and residual deviance. Applying cutoffs of 0.15, 0.20, and 0.25 to Model 3's predictions achieved accuracies of 65.31%, 74.94%, and 77.45% respectively. Therefore, a cutoff of 0.25 was determined to be optimal for classifying loan applications as approved or declined.
The document describes developing a logistic regression model to predict credit risk. It outlines preprocessing steps like binning variables, handling missing data, and sampling training data. Three models are developed: Model 1 uses binned variables and imputed missing data, Model 2 is similar but bins missing data, and Model 3 uses original variables. Model 1 outputs the logit function and identifies key predictor variables as number of late payments, open accounts, and binned age, debt ratio, and credit utilization variables.
The document discusses how using verified income and employment data from The Work Number can help lenders and dealers make more informed credit decisions when approving auto loans, especially for subprime borrowers. It summarizes research showing that factors like income verification, job tenure, pay frequency, and recent employment disruptions are highly predictive of loan performance but often under-reported on applications. Incorporating comprehensive and regularly updated data from The Work Number can help lower risks, customize loan terms, increase approval rates, and improve portfolio performance for lenders.
Historical Credit Data | Total Credit Card SpendExperian
Find out how much your customers are spending on their credit cards with trended data. Understanding consumers’ past behavior is crucial to understanding their credit preferences, their potential risks and for developing a strategy for the future. Trended Solutions: Give your customers credit for their history.
Do rating agencies cater evidence from rating based contractsMr HP
This summary provides the key points from the document in 3 sentences:
Rating agencies may provide inflated credit ratings to borrowers with rating-based loan contracts in order to cater to their business interests, as downgrades could negatively impact the borrowers' cash flows. The study finds evidence that rating agencies' adjustments for off-balance sheet debt and soft factors are more favorable for borrowers with rating-based contracts compared to accounting-ratio based contracts. However, the degree of rating inflation is reduced when rating agencies face higher reputational costs, such as when ratings are close to thresholds or another rating agency also provides a rating.
Juliet documented her weekend activities with Gemma in January 2010. The entries show that they went shopping at IKEA, played Nintendo DS, read to Londie, had breakfast, played darts, ate spaghetti for dinner, played with budgie Juanita, and worked out.
Monarch Industrial Products manufactures metal reclamation putties and sticks that can be used to repair machinery and process equipment. The putties are two-component epoxy mixtures that harden into a firm material that adheres strongly to surfaces. They allow repairs to be made in around two hours of downtime, saving on replacement costs. The putties rehabilitate surfaces rather than requiring replacement and avoid dangers from hot work. They provide fast, economical, and permanent repairs that increase reliability and reduce plant shutdown costs.
Akkanto is a Brussels-based communication consultancy that provides strategic communication advice and effective implementation to clients. It has a team of 26 professionals with diverse backgrounds. Services include corporate communications, public affairs, crisis communications, media relations, and financial communications. Clients include large multinational companies and Belgian governmental organizations.
The document discusses tips for reducing anxiety when giving presentations. It emphasizes the importance of thorough preparation, including rehearsing your presentation, understanding your audience, and customizing your message. Proper preparation helps ensure you feel confident and your audience understands your key points. The document also provides advice on delivery techniques like maintaining eye contact, varying vocal tones, and avoiding distracting mannerisms.
The document provides guidance on building effective online courses by starting with course goals and the instructor's teaching style, using a learner-centered approach, and ensuring clear organization and interaction. It emphasizes understanding students, applying principles of good teaching, and using instructional design steps that include analysis, design, development and evaluation of the course. The document also discusses engaging students through varied content delivery, collaboration activities, and addressing different learning needs.
Artificial intelligence (AI) is everywhere, promising self-driving cars, medical breakthroughs, and new ways of working. But how do you separate hype from reality? How can your company apply AI to solve real business problems?
Here’s what AI learnings your business should keep in mind for 2017.
https://ijitce.com/index.php
Our journal maintains rigorous peer review standards. Each submitted article undergoes a thorough evaluation by experts in the respective field. This stringent review process helps ensure that only high-quality and scientifically sound research is accepted for publication. Researchers can trust that the articles they find in IJITCE have been critically assessed for validity, significance, and originality.
International journal of engineering and mathematical modelling vol1 no1_2015_2IJEMM
This document discusses using the CIR++ model to estimate default risk through simulation. It begins by describing structural and reduced-form approaches to default estimation. It then introduces the CIR and CIR++ processes, which can model the evolution of short-term interest rates and default intensities. The document outlines how the CIR++ model can be calibrated to market data on yield curves and credit default swap prices to estimate default probabilities. It concludes by stating the calibrated CIR++ model will be tested against Deutsche Bank estimates to evaluate its ability to model default risk.
This document discusses using artificial intelligence to analyze the credit market and provide insights into how credit spreads and treasury yields may perform under different economic scenarios. Specifically, it asks an AI system to analyze what would happen if: 1) the output gap remains below zero, 2) there is a strong economic recovery in response to stimulus, and 3) the Fed reverts emergency rate cuts after 5-7 months. The AI system indicates there is initial risk of spread widening and yield compression, followed by spread improvement as the economy recovers, and then opposing moves in spreads and yields as rates increase. It concludes that credit spreads face upward risk over the next 3-4 months based on macroeconomic factors.
This document discusses common myths about credit scores and summarizes research from Equifax on credit score trends. It addresses three myths: 1) That there is only one credit score, when in reality there are many potential scores from different credit bureaus and models. 2) That credit scores are permanent, when in fact they fluctuate based on financial behaviors and can change significantly over time periods as short as 3 months. 3) That high income or wealth guarantees a good credit score, when research shows income and credit scores are not strongly correlated and high earners can still have low scores while low earners can have high scores.
Transaction scoring can help credit card issuers more accurately assess risk and identify opportunities. It does this by analyzing transaction data in real time to identify risky spending patterns or positive credit usage. This allows issuers to intervene earlier with at-risk accounts and guide customers toward responsible credit use. It also reduces "false positives," identifying customers suitable for cross-selling or promotions. Transaction scoring provides benefits to both issuers and consumers by enabling more precise segmentation and tailored account management strategies.
This document discusses analyzing the relationship between underwriting techniques used by two credit managers at a mortgage company. It will examine if loans underwritten by one credit manager contain more conditions than the other, and if loans with higher credit grades or lower loan-to-value ratios receive fewer conditions. The analysis will involve comparing quantitative variables like credit grade, loan-to-value ratio, and number of conditions against each other using charts. It aims to determine if risk-based underwriting is consistently applied, or if one credit manager applies conditions inconsistently with risk levels.
Factors Factors Influencing Credit Risk For Small And Medium Enterprise Loans...paperpublications3
Abstract: There has been an increased concern over high credit risk for small and medium enterprise loan in financial institutions. High interest rates, credit rating, recovery mechanisms and business experience play an important role in influencing credit risk for small and medium enterprise loans. The main objective of this study was to investigate factors influencing credit risk for small and medium enterprise loans a survey of banks in Kitale Town, Kenya. The specific objectives of the study were: To establish the influence of interest rates on credit risk of small and medium enterprise loans in banks, bto find out the influence of credit rating in credit risk of small and medium enterprise loans in banks, to establish the influence of recovery mechanism in credit risk of small and medium enterprise loans in banks, and to assess the influence of business experience in credit risk of small and medium enterprise loans in banks. Credit management theory, trade-off theory, modern portfolio theory were used to underpin the study. Explanatory research design was used in this study. The study targeted 331 employees from 11 Commercial Banks in Kitale. The study used stratified sampling technique. Interest rates, credit rating, recovery mechanism and business experience were taken as the independent variables while credit risk was the dependent variable. Pilot study was used to test the validity and reliability of the research instrument. Interest rates showed a positive and significant effect on credit risk (β= 0.153, ρ<0.05).><0.05).><0.05).><0.05). In conclusion, the study has established that whenever there are high short-term interest rates, there is an increase in credit risk. In addition, interest rate shifts are heterogeneous across the firm and have different implications for leverage and default in the short run than in the longer run. Hence the study recommends for need for a comprehensive risk management process that ensures the timely identification, measurement, monitoring, and control of risk.
Machine Learning Project - Default credit card clients Vatsal N Shah
- The model we built here will use all possible factors to predict data on customers to find who are defaulters and non‐defaulters next month.
- The goal is to find the whether the clients are able to pay their next month credit amount.
- Identify some potential customers for the bank who can settle their credit balance.
- To determine if their customers could make the credit card payments on‐time.
- Default is the failure to pay interest or principal on a loan or credit card payment.
Real options analysis (ROA) has several advantages over traditional decision making techniques for valuation and investment decisions under uncertainty. [1] ROA accounts for flexibility to modify decisions as new information arises, rather than viewing decisions as binary choices. [2] It uses stochastic processes and only considers favorable outcomes, avoiding the need to heavily discount cash flows or select a discount rate. [3] ROA thus treats uncertainty as a profit opportunity rather than something to avoid or overcorrect for.
This document describes a project using logistic regression to model credit risk. The student built three logistic regression models using different independent variables from a dataset of 29092 loan applications. Model 3, using loan amount, interest rate, grade of employment, employment length, annual income, age, and home ownership, had the lowest AIC score and residual deviance. Applying cutoffs of 0.15, 0.20, and 0.25 to Model 3's predictions achieved accuracies of 65.31%, 74.94%, and 77.45% respectively. Therefore, a cutoff of 0.25 was determined to be optimal for classifying loan applications as approved or declined.
The document describes developing a logistic regression model to predict credit risk. It outlines preprocessing steps like binning variables, handling missing data, and sampling training data. Three models are developed: Model 1 uses binned variables and imputed missing data, Model 2 is similar but bins missing data, and Model 3 uses original variables. Model 1 outputs the logit function and identifies key predictor variables as number of late payments, open accounts, and binned age, debt ratio, and credit utilization variables.
The document discusses how using verified income and employment data from The Work Number can help lenders and dealers make more informed credit decisions when approving auto loans, especially for subprime borrowers. It summarizes research showing that factors like income verification, job tenure, pay frequency, and recent employment disruptions are highly predictive of loan performance but often under-reported on applications. Incorporating comprehensive and regularly updated data from The Work Number can help lower risks, customize loan terms, increase approval rates, and improve portfolio performance for lenders.
Historical Credit Data | Total Credit Card SpendExperian
Find out how much your customers are spending on their credit cards with trended data. Understanding consumers’ past behavior is crucial to understanding their credit preferences, their potential risks and for developing a strategy for the future. Trended Solutions: Give your customers credit for their history.
Do rating agencies cater evidence from rating based contractsMr HP
This summary provides the key points from the document in 3 sentences:
Rating agencies may provide inflated credit ratings to borrowers with rating-based loan contracts in order to cater to their business interests, as downgrades could negatively impact the borrowers' cash flows. The study finds evidence that rating agencies' adjustments for off-balance sheet debt and soft factors are more favorable for borrowers with rating-based contracts compared to accounting-ratio based contracts. However, the degree of rating inflation is reduced when rating agencies face higher reputational costs, such as when ratings are close to thresholds or another rating agency also provides a rating.
Juliet documented her weekend activities with Gemma in January 2010. The entries show that they went shopping at IKEA, played Nintendo DS, read to Londie, had breakfast, played darts, ate spaghetti for dinner, played with budgie Juanita, and worked out.
Monarch Industrial Products manufactures metal reclamation putties and sticks that can be used to repair machinery and process equipment. The putties are two-component epoxy mixtures that harden into a firm material that adheres strongly to surfaces. They allow repairs to be made in around two hours of downtime, saving on replacement costs. The putties rehabilitate surfaces rather than requiring replacement and avoid dangers from hot work. They provide fast, economical, and permanent repairs that increase reliability and reduce plant shutdown costs.
Akkanto is a Brussels-based communication consultancy that provides strategic communication advice and effective implementation to clients. It has a team of 26 professionals with diverse backgrounds. Services include corporate communications, public affairs, crisis communications, media relations, and financial communications. Clients include large multinational companies and Belgian governmental organizations.
The document discusses tips for reducing anxiety when giving presentations. It emphasizes the importance of thorough preparation, including rehearsing your presentation, understanding your audience, and customizing your message. Proper preparation helps ensure you feel confident and your audience understands your key points. The document also provides advice on delivery techniques like maintaining eye contact, varying vocal tones, and avoiding distracting mannerisms.
The document provides guidance on building effective online courses by starting with course goals and the instructor's teaching style, using a learner-centered approach, and ensuring clear organization and interaction. It emphasizes understanding students, applying principles of good teaching, and using instructional design steps that include analysis, design, development and evaluation of the course. The document also discusses engaging students through varied content delivery, collaboration activities, and addressing different learning needs.
Artificial intelligence (AI) is everywhere, promising self-driving cars, medical breakthroughs, and new ways of working. But how do you separate hype from reality? How can your company apply AI to solve real business problems?
Here’s what AI learnings your business should keep in mind for 2017.
https://ijitce.com/index.php
Our journal maintains rigorous peer review standards. Each submitted article undergoes a thorough evaluation by experts in the respective field. This stringent review process helps ensure that only high-quality and scientifically sound research is accepted for publication. Researchers can trust that the articles they find in IJITCE have been critically assessed for validity, significance, and originality.
International journal of engineering and mathematical modelling vol1 no1_2015_2IJEMM
This document discusses using the CIR++ model to estimate default risk through simulation. It begins by describing structural and reduced-form approaches to default estimation. It then introduces the CIR and CIR++ processes, which can model the evolution of short-term interest rates and default intensities. The document outlines how the CIR++ model can be calibrated to market data on yield curves and credit default swap prices to estimate default probabilities. It concludes by stating the calibrated CIR++ model will be tested against Deutsche Bank estimates to evaluate its ability to model default risk.
This document discusses using artificial intelligence to analyze the credit market and provide insights into how credit spreads and treasury yields may perform under different economic scenarios. Specifically, it asks an AI system to analyze what would happen if: 1) the output gap remains below zero, 2) there is a strong economic recovery in response to stimulus, and 3) the Fed reverts emergency rate cuts after 5-7 months. The AI system indicates there is initial risk of spread widening and yield compression, followed by spread improvement as the economy recovers, and then opposing moves in spreads and yields as rates increase. It concludes that credit spreads face upward risk over the next 3-4 months based on macroeconomic factors.
This document discusses common myths about credit scores and summarizes research from Equifax on credit score trends. It addresses three myths: 1) That there is only one credit score, when in reality there are many potential scores from different credit bureaus and models. 2) That credit scores are permanent, when in fact they fluctuate based on financial behaviors and can change significantly over time periods as short as 3 months. 3) That high income or wealth guarantees a good credit score, when research shows income and credit scores are not strongly correlated and high earners can still have low scores while low earners can have high scores.
Transaction scoring can help credit card issuers more accurately assess risk and identify opportunities. It does this by analyzing transaction data in real time to identify risky spending patterns or positive credit usage. This allows issuers to intervene earlier with at-risk accounts and guide customers toward responsible credit use. It also reduces "false positives," identifying customers suitable for cross-selling or promotions. Transaction scoring provides benefits to both issuers and consumers by enabling more precise segmentation and tailored account management strategies.
This document discusses analyzing the relationship between underwriting techniques used by two credit managers at a mortgage company. It will examine if loans underwritten by one credit manager contain more conditions than the other, and if loans with higher credit grades or lower loan-to-value ratios receive fewer conditions. The analysis will involve comparing quantitative variables like credit grade, loan-to-value ratio, and number of conditions against each other using charts. It aims to determine if risk-based underwriting is consistently applied, or if one credit manager applies conditions inconsistently with risk levels.
Reply to DiscussionsD1 navyaA bank failure is the ending of.docxchris293
Reply to Discussions
D1: navya
A bank failure is the ending of an insolvent bank by a state or federal regulator. So the only power that closes the national banks is the comptroller who has a higher power in maintaining the currency. It mainly happens when a bank fails where it is assumed by the federal deposit insurance corporation in the insures of deposits. They find a different bank to take it over because various customers will specifically like the continuation using their debit cards, online banking tools, and accounts. So bank failures are mainly often to predict because the federal deposit insurance commission will not announce a particular bank to set go under the profits. Then bank diversification is the procedure that allocates the capital in a specific way because it reduces the exposure to a particular asset or risk. Therefore, the main reason for this bank diversification is to decrease the volatility or risk by investing in various assets (Goetz, 2012).
So considering both of those banking systems can easily relate to the country's economic health by determining the better quality of the loan book of different individual books. Then for maintaining the better quality of advance bank portfolio, there is only one crucial tool where it is credit monitoring. Credit monitoring plays a vital role in protecting the bank's exposures, but it also ensures the various funds that are channeled by maintaining the right purpose. It mainly acts as the guardrail for ensuring the health of banks and countries economically to stay in the right trajectory. Then various technology solutions will be readily available in the market for helping the automated process of credit monitoring to a large extent. They can ensure the functions of credit monitoring to keep the process and objective in the method oriented (Brownbridge, 2002).
References
Brownbridge, M. (2002). Resolving Bank Failures in Uganda: Policy Lessons from Recent Bank Failures. Development Policy Review, 20(3), 279-291. doi: 10.1111/1467-7679.00171
Goetz, M. (2012). Bank Diversification, Market Structure and Bank Risk Taking: Theory and Evidence from U.S. Commercial Banks. SSRN Electronic Journal. doi: 10.2139/ssrn.2651161
Reply:
D2: pavani
Diversification helps individual institutions and makes them be benefited. But Wagner says that the systematic risk increases by the degree of diversification. Raffestin also said something about the diversification that diversification can cause risks and any number of failures also. By the above words, we can know the negative aspects or negative effects of diversification. Systematic risks are very broad and complex term. This diversification process has some of the diversification measures. The indicator of diversification is calculated from the bank’s profitability. There are various methods of diversification. Commonly Alas et al proposed method is used (Mirzaei & Kutan, 2016).
And also the weight average diversification of banks ( AWDI.
This presentation provides complete study ofcredit risk management,how it was performed in yester years ,how it is taken care nowadays and what is the road ahead in future
Credit Audit's Use of Data Analytics in Examining Consumer Loan PortfoliosJacob Kosoff
Written by Jacob Kosoff and published in September 2013 by the RMA Journal. This article describes banks in 2012 & 2013 were modernizing their Credit Review functions.
Chapter 24_Risk Management in Financial InstitutionsRusman Mukhlis
This document summarizes techniques for managing credit risk and interest rate risk at financial institutions. It discusses screening, monitoring and specializing in lending to manage credit risk. It then introduces income gap analysis and duration gap analysis to measure interest rate risk exposure and impact on income and capital. Strategies discussed to manage interest rate risk include shortening asset duration, lengthening liability duration, and immunizing the balance sheet by setting the duration gap to zero.
Consumer Credit Scoring Using Logistic Regression and Random ForestHirak Sen Roy
The document discusses using logistic regression and random forest models for consumer credit scoring. It begins by introducing credit scoring and explaining that the goal is to classify applicants as "good" or "bad" credit risks. It then outlines the typical steps taken in developing a credit scoring model, including understanding the problem, defining variables, exploratory data analysis, and splitting data into training and test sets. The document focuses on logistic regression, explaining the logistic regression model and how it is fitted. It also briefly introduces random forest methods and LASSO regularization.
This document summarizes a study examining the role of borrower reputation in mitigating adverse selection and moral hazard in the subprime mortgage market leading up to the 2007-2008 financial crisis. The study uses data from a major subprime lender to analyze the differences between full documentation and low documentation loans. It finds that while low documentation loans performed worse, this effect was strongest for low-doc loans to W2 borrowers who could have obtained full-doc loans. However, for self-employed borrowers who relied on low-doc loans for credit access, there was little difference in performance between loan types. This suggests reputation concerns constrained adverse selection and income exaggeration for self-employed borrowers on low-doc loans. The
The document discusses how regulatory changes since the Great Recession have impacted the credit risk assessment process in equipment financing. It interviews three credit managers who say that while fundamental underwriting processes haven't changed, there is now a greater focus on regulatory compliance, more robust risk frameworks, adjusting to client needs, and managing shared risk between credit and business lines. They also discuss managing competitive pressures by selectively adjusting pricing and terms, as well as ensuring younger credit managers can assess long-term risks despite not having lived through previous economic downturns themselves.
Financial incentives and loan officer behavior: multitasking and allocation o...FGV Brazil
We investigate the implications of providing loan officers with a compensation structure that rewards loan volume and penalizes poor performance. Using a unique data set provided by a large international commercial bank, we examine the three main activities that loan officers perform: monitoring, origination, and screening. We find that when loan officers are at risk of losing their bonus, they increase monitoring and origination, but not screening effort. On the other hand, having lost a bonus in the previous period does not entail higher effort. We document unintended consequences of the incentive contract showing the incompleteness of such contracts.
Date: 2015
Authors:
Behr, Patrick Gottfried
Drexler, Alejandro
Gropp, Reint
Guettler, Andre
This document discusses modeling overdraft behavior by income level using data from a local bank. The authors aim to provide a statistical framework to analyze whether low-income customers disproportionately use overdraft services compared to middle- and high-income customers, as regulators have claimed. Simple analyses of the data show that low-income households account for 29% of overdraft fees but 34% of accounts, and that overdraft patterns look similar across income levels. However, the authors argue a more robust statistical approach is needed to accurately assess differences between income groups.
Fair Isaac developed credit scoring models that analyze over 100 predictive variables from a consumer's credit report to assess credit risk. The top 5 categories that determine a score are: (1) payment history, (2) amounts owed, (3) length of credit history, (4) new credit, and (5) types of credit in use. Inquiries are also considered but have a small impact. Reason codes identify areas that most affected a consumer's score to help them improve their credit over time.
Similar to A Statistical/Mathematical Approach to Enhanced Loan Modification Targeting (20)
Using Adaptive Scrum to Tame Process Reverse Engineering in Data Analytics Pr...Cognizant
Organizations rely on analytics to make intelligent decisions and improve business performance, which sometimes requires reproducing business processes from a legacy application to a digital-native state to reduce the functional, technical and operational debts. Adaptive Scrum can reduce the complexity of the reproduction process iteratively as well as provide transparency in data analytics porojects.
Data Modernization: Breaking the AI Vicious Cycle for Superior Decision-makingCognizant
The document discusses how most companies are not fully leveraging artificial intelligence (AI) and data for decision-making. It finds that only 20% of companies are "leaders" in using AI for decisions, while the remaining 80% are stuck in a "vicious cycle" of not understanding AI's potential, having low trust in AI, and limited adoption. Leaders use more sophisticated verification of AI decisions and a wider range of AI technologies beyond chatbots. The document provides recommendations for breaking the vicious cycle, including appointing AI champions, starting with specific high-impact decisions, and institutionalizing continuous learning about AI advances.
It Takes an Ecosystem: How Technology Companies Deliver Exceptional ExperiencesCognizant
Experience is becoming a key strategy for technology companies as they shift to cloud-based subscription models. This requires building an "experience ecosystem" that breaks down silos and involves partners. Building such an ecosystem involves adopting a cross-functional approach to experience, making experience data-driven to generate insights, and creating platforms to enable connected selling between companies and partners.
Intuition is not a mystery but rather a mechanistic process based on accumulated experience. Leading businesses are engineering intuition into their organizations by harnessing machine learning software, massive cloud processing power, huge amounts of data, and design thinking in experiences. This allows them to anticipate and act with speed and insight, improving decision making through data-driven insights and acting as if on intuition.
The Work Ahead: Transportation and Logistics Delivering on the Digital-Physic...Cognizant
The T&L industry appears poised to accelerate its long-overdue modernization drive, as the pandemic spurs an increased need for agility and resilience, according to our study.
Enhancing Desirability: Five Considerations for Winning Digital InitiativesCognizant
To be a modern digital business in the post-COVID era, organizations must be fanatical about the experiences they deliver to an increasingly savvy and expectant user community. Getting there requires a mastery of human-design thinking, compelling user interface and interaction design, and a focus on functional and nonfunctional capabilities that drive business differentiation and results.
The Work Ahead in Manufacturing: Fulfilling the Agility MandateCognizant
Manufacturers are ahead of other industries in IoT deployments but lag in investments in analytics and AI needed to maximize IoT's benefits. While many have IoT pilots, few have implemented machine learning at scale to analyze sensor data and optimize processes. To fully digitize manufacturing, investments in automation, analytics, and AI must increase from the current 5.5% of revenue to over 11% to integrate IT, OT, and PT across the value chain.
The Work Ahead in Higher Education: Repaving the Road for the Employees of To...Cognizant
Higher-ed institutions expect pandemic-driven disruption to continue, especially as hyperconnectivity, analytics and AI drive personalized education models over the lifetime of the learner, according to our recent research.
Engineering the Next-Gen Digital Claims Organisation for Australian General I...Cognizant
The document discusses potential future states for the claims organization of Australian general insurers. It notes that gradual changes like increasing climate volatility, new technologies, and changing customer demographics will reshape the insurance industry and claims processes. Five potential end states for claims organizations are described: 1) traditional claims will demand faster processing; 2) a larger percentage of claims will come from new digital risks; 3) claims processes may become "Uberized" through partnerships; 4) claims organizations will face challenges in risk management propositions; 5) humans and machines will work together to adjudicate claims using large data and computing power. The document argues that insurers must transform claims through digital technologies to concurrently improve customer experience, operational effectiveness, and efficiencies
Profitability in the Direct-to-Consumer Marketplace: A Playbook for Media and...Cognizant
Amid constant change, industry leaders need an upgraded IT infrastructure capable of adapting to audience expectations while proactively anticipating ever-evolving business requirements.
Green Rush: The Economic Imperative for SustainabilityCognizant
Green business is good business, according to our recent research, whether for companies monetizing tech tools used for sustainability or for those that see the impact of these initiatives on business goals.
Policy Administration Modernization: Four Paths for InsurersCognizant
The pivot to digital is fraught with numerous obstacles but with proper planning and execution, legacy carriers can update their core systems and keep pace with the competition, while proactively addressing customer needs.
The Work Ahead in Utilities: Powering a Sustainable Future with DigitalCognizant
Utilities are starting to adopt digital technologies to eliminate slow processes, elevate customer experience and boost sustainability, according to our recent study.
AI in Media & Entertainment: Starting the Journey to ValueCognizant
Up to now, the global media & entertainment industry (M&E) has been lagging most other sectors in its adoption of artificial intelligence (AI). But our research shows that M&E companies are set to close the gap over the coming three years, as they ramp up their investments in AI and reap rising returns. The first steps? Getting a firm grip on data – the foundation of any successful AI strategy – and balancing technology spend with investments in AI skills.
Operations Workforce Management: A Data-Informed, Digital-First ApproachCognizant
As #WorkFromAnywhere becomes the rule rather than the exception, organizations face an important question: How can they increase their digital quotient to engage and enable a remote operations workforce to work collaboratively to deliver onclient requirements and contractual commitments?
Five Priorities for Quality Engineering When Taking Banking to the CloudCognizant
As banks move to cloud-based banking platforms for lower costs and greater agility, they must seamlessly integrate technologies and workflows while ensuring security, performance and an enhanced user experience. Here are five ways cloud-focused quality assurance helps banks maximize the benefits.
Getting Ahead With AI: How APAC Companies Replicate Success by Remaining FocusedCognizant
Changing market dynamics are propelling Asia-Pacific businesses to take a highly disciplined and focused approach to ensuring that their AI initiatives rapidly scale and quickly generate heightened business impact.
The Work Ahead in Intelligent Automation: Coping with Complexity in a Post-Pa...Cognizant
Intelligent automation continues to be a top driver of the future of work, according to our recent study. To reap the full advantages, businesses need to move from isolated to widespread deployment.
STREETONOMICS: Exploring the Uncharted Territories of Informal Markets throug...sameer shah
Delve into the world of STREETONOMICS, where a team of 7 enthusiasts embarks on a journey to understand unorganized markets. By engaging with a coffee street vendor and crafting questionnaires, this project uncovers valuable insights into consumer behavior and market dynamics in informal settings."
New Visa Rules for Tourists and Students in Thailand | Amit Kakkar Easy VisaAmit Kakkar
Discover essential details about Thailand's recent visa policy changes, tailored for tourists and students. Amit Kakkar Easy Visa provides a comprehensive overview of new requirements, application processes, and tips to ensure a smooth transition for all travelers.
Discover the Future of Dogecoin with Our Comprehensive Guidance36 Crypto
Learn in-depth about Dogecoin's trajectory and stay informed with 36crypto's essential and up-to-date information about the crypto space.
Our presentation delves into Dogecoin's potential future, exploring whether it's destined to skyrocket to the moon or face a downward spiral. In addition, it highlights invaluable insights. Don't miss out on this opportunity to enhance your crypto understanding!
https://36crypto.com/the-future-of-dogecoin-how-high-can-this-cryptocurrency-reach/
Vicinity Jobs’ data includes more than three million 2023 OJPs and thousands of skills. Most skills appear in less than 0.02% of job postings, so most postings rely on a small subset of commonly used terms, like teamwork.
Laura Adkins-Hackett, Economist, LMIC, and Sukriti Trehan, Data Scientist, LMIC, presented their research exploring trends in the skills listed in OJPs to develop a deeper understanding of in-demand skills. This research project uses pointwise mutual information and other methods to extract more information about common skills from the relationships between skills, occupations and regions.
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...Donc Test
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby, Hodge, Verified Chapters 1 - 13, Complete Newest Version Solution Manual For Financial Accounting, 8th Canadian Edition by Libby, Hodge, Verified Chapters 1 - 13, Complete Newest Version Solution Manual For Financial Accounting 8th Canadian Edition Pdf Chapters Download Stuvia Solution Manual For Financial Accounting 8th Canadian Edition Ebook Download Stuvia Solution Manual For Financial Accounting 8th Canadian Edition Pdf Solution Manual For Financial Accounting 8th Canadian Edition Pdf Download Stuvia Financial Accounting 8th Canadian Edition Pdf Chapters Download Stuvia Financial Accounting 8th Canadian Edition Ebook Download Stuvia Financial Accounting 8th Canadian Edition Pdf Financial Accounting 8th Canadian Edition Pdf Download Stuvia
5 Tips for Creating Standard Financial ReportsEasyReports
Well-crafted financial reports serve as vital tools for decision-making and transparency within an organization. By following the undermentioned tips, you can create standardized financial reports that effectively communicate your company's financial health and performance to stakeholders.
University of North Carolina at Charlotte degree offer diploma Transcripttscdzuip
办理美国UNCC毕业证书制作北卡大学夏洛特分校假文凭定制Q微168899991做UNCC留信网教留服认证海牙认证改UNCC成绩单GPA做UNCC假学位证假文凭高仿毕业证GRE代考如何申请北卡罗莱纳大学夏洛特分校University of North Carolina at Charlotte degree offer diploma Transcript
Abhay Bhutada, the Managing Director of Poonawalla Fincorp Limited, is an accomplished leader with over 15 years of experience in commercial and retail lending. A Qualified Chartered Accountant, he has been pivotal in leveraging technology to enhance financial services. Starting his career at Bank of India, he later founded TAB Capital Limited and co-founded Poonawalla Finance Private Limited, emphasizing digital lending. Under his leadership, Poonawalla Fincorp achieved a 'AAA' credit rating, integrating acquisitions and emphasizing corporate governance. Actively involved in industry forums and CSR initiatives, Abhay has been recognized with awards like "Young Entrepreneur of India 2017" and "40 under 40 Most Influential Leader for 2020-21." Personally, he values mindfulness, enjoys gardening, yoga, and sees every day as an opportunity for growth and improvement.
OJP data from firms like Vicinity Jobs have emerged as a complement to traditional sources of labour demand data, such as the Job Vacancy and Wages Survey (JVWS). Ibrahim Abuallail, PhD Candidate, University of Ottawa, presented research relating to bias in OJPs and a proposed approach to effectively adjust OJP data to complement existing official data (such as from the JVWS) and improve the measurement of labour demand.
"Does Foreign Direct Investment Negatively Affect Preservation of Culture in the Global South? Case Studies in Thailand and Cambodia."
Do elements of globalization, such as Foreign Direct Investment (FDI), negatively affect the ability of countries in the Global South to preserve their culture? This research aims to answer this question by employing a cross-sectional comparative case study analysis utilizing methods of difference. Thailand and Cambodia are compared as they are in the same region and have a similar culture. The metric of difference between Thailand and Cambodia is their ability to preserve their culture. This ability is operationalized by their respective attitudes towards FDI; Thailand imposes stringent regulations and limitations on FDI while Cambodia does not hesitate to accept most FDI and imposes fewer limitations. The evidence from this study suggests that FDI from globally influential countries with high gross domestic products (GDPs) (e.g. China, U.S.) challenges the ability of countries with lower GDPs (e.g. Cambodia) to protect their culture. Furthermore, the ability, or lack thereof, of the receiving countries to protect their culture is amplified by the existence and implementation of restrictive FDI policies imposed by their governments.
My study abroad in Bali, Indonesia, inspired this research topic as I noticed how globalization is changing the culture of its people. I learned their language and way of life which helped me understand the beauty and importance of cultural preservation. I believe we could all benefit from learning new perspectives as they could help us ideate solutions to contemporary issues and empathize with others.
Economic Risk Factor Update: June 2024 [SlideShare]Commonwealth
May’s reports showed signs of continued economic growth, said Sam Millette, director, fixed income, in his latest Economic Risk Factor Update.
For more market updates, subscribe to The Independent Market Observer at https://blog.commonwealth.com/independent-market-observer.
Economic Risk Factor Update: June 2024 [SlideShare]
A Statistical/Mathematical Approach to Enhanced Loan Modification Targeting
1. A Statistical/Mathematical Approach to
Enhanced Loan Modification Targeting
Rising home prices may play a larger role than factors such as job
loss in determining which consumers are less likely to re-default on
modified home loans.
Executive Summary
When the housing bubble burst in 2007, millions of
homeowners entered foreclosure and default. To
reduce the burden of such defaults on borrowers,
lenders and the economy, many banks introduced
loan modification programs, such as writing down
a portion of the loan, reducing interest rates or
extending payment terms.
However, within six months of such loan modifi-
cations, a significant percent of borrowers had
defaulted.1
This is bad for all concerned. This white
paper describes a simple and effective combina-
tion of statistical and mathematical techniques
that more accurately determine when and for
whom it is most effective to modify loans. These
techniques accurately separate the effects of
various factors in predicting borrower behavior.
They suggest that rising home prices should be
given more weight in choosing which borrowers
will successfully repay their loans when given
loan modifications.
Loan Modification: The Challenges
Numerous business and market challenges make
banks and other lenders reluctant to offer loan
modifications. The first is identifying the type of
modification (e.g., a lower interest rate, writing off
a portion of the principal, a longer payment term
or a combination of these) that is most beneficial
for the lender and the borrower — and will be most
effective in assuring the borrower continues to
make loan payments on time.
The second challenge is determining whether
there are greater financial benefits to the lender
in allowing a borrower to default or whether
the cost of a lower interest rate or principal, or
longer payment terms, is justified by the eventual
repayment of the loan. The third challenge is to
estimate the risk that any given borrower will
re-default, and to identify those who have both
the ability and willingness to pay. This white paper
addresses this third question of identifying which
borrowers are most likely to re-default.
Prior research clearly shows the link between
a property with negative equity (i.e., being
“underwater”) and its move into foreclosure.2,3,4
If a borrower has sufficient equity in his home,
he has the option of a second mortgage to stay
current with the terms of his loan in the event of a
job loss or medical emergency. While the strength
of this link varies from borrower to borrower, we
assume for the sake of this paper that the value
of the property is one of the prime determinants
of whether borrowers will default.
We also, however, assume that “trigger events”
including loss of income, unemployment and
events such as economic recession also influence
• Cognizant 20-20 Insights
cognizant 20-20 insights | may 2014
2. 2
the default decision. So do borrower attributes
such as the borrower’s credit score, age, education,
marital status and type of loan (e.g., the interest
rate, adjustable vs. fixed, etc.)
Our Analytical Approach
Performance data on the aftermath of loan modi-
fications is scarce. However, using data about the
customer’s behavior before his loan was modified
is technically equivalent to using post-loan-mod-
ification data to determine the probability he will
default.
We perform our analysis by estimating a second
order Markov chain/transition matrix. This differs
from traditional prediction techniques in that it
considers only the borrower’s most recent state
(i.e., his demonstrated willingness and ability to
pay) rather than his long-term history in order
to predict future behavior and thus what sort of
loan modification, if any, he should receive. Our
hypothesis, which has been demonstrated by
application of this technique, is that this analysis
produces more accurate results than traditional
methods such as credit scoring or long-term
analysis of payment behaviors.
Conditional probabilities can be estimated by
either multinomial logistic regression (which
assumes the same set of variables influence all
state equations) or binomial logistic regression
(and rescaling so that the range of probabilities
add up to 1 by applying the Begg-Gray method).5
Either of these techniques allows the effects
of loans that end early due to prepayment to
be separated from those that end early due to
default.
Let’s illustrate with a numerical example. Using
loan level data we build a multinomial logistic
model. The dependent variables are (Current /
60+ Delq), (30+ Delq / 60+ Delq), (60+ Delq / 60+
Delq), (90+ Delq / 60+ Delq) and (Default / 60+
Delq). Note that (Current / 60+ Delq) describes
a loan with 60+ delq which was more than two
months delinquent but is now back to a current
state.
Figure 1 is a transition matrix estimated from
the logistic model equations for a loan with the
ID of “X.” In the top left corner, 0.6 signifies that
this loan with the ID of “X” was more than three
months delinquent but is now current, with the
probability the borrower will remain current
estimated at 0.60.
This table also shows how the second order
Markov chain is helpful in predicting a borrower’s
re-default risk. In other words, which combina-
tion of factor values is most likely to put them
into either a delinquent or nondelinquent state.
For example, we know that a borrower’s debt-to-
income (DTI) ratio is one of the determinants in
a default decision and is linearly related to the
probability of default (the higher the DTI, the
higher the probability of default). Keeping all
other factors constant we can thus estimate the
highest level of DTI at which the borrower will
remain nondelinquent. Here we have chosen 60+
delq as that level, based on observed trends.
This matrix can be used to predict either long-term
or average behavior of a borrower using simple
linear algebra. Rearranging the matrix so rows and
columns of the absorbing state come first provides
a canonical form, dividing the transition matrix
into four sub-matrices (as shown in Figure 2).
Note that In is the square identity matrix if there
is more than one observing state. Otherwise,
the scalar and 0 is zero matrix. The fundamen-
tal matrix is defined as F = (I - Q)-1
, which gives
the average number of months that the borrower
stays on the books before the borrower defaults
and the lender writes off the loan.
cognizant 20-20 insights
Second Order Transition Matrix
Figure 1
State Current 30+ Delq 60+ Delq 90+ Delq Default
(Current / 60+ Delq) 0.6 0.3 0.1 0 0
(30+ Delq / 60+ Delq) 0.5 0.4 0.05 0.05 0
(60+ Delq / 60+ Delq) 0.2 0.3 0.4 0.1 0
(90+ Delq / 60+ Delq) 0.05 0.05 0.1 0.5 0.3
(Default / 60+ Delq) 0 0 0 0 1
3. 3cognizant 20-20 insights
We can now answer how long a borrower will stay
current on their loan if he started with a current
state which is the sum of the first row (i.e., 30.23
+ 18.98 + 7.17 + 3.33 = 59.7 months). Similarly,
if he starts with 30+ Delq, 60+ Delq and 90+
Delq, he stays current for 58, 54 and 24 months
respectively.
Conclusion
Lenders originate loans according to the risk
associated with each borrower — in other words,
pricing the risk. However unforeseen factors such
as job loss, a decline in home prices or recession
can force large numbers of borrowers into
defaults.
The success of loan modification programs
designed to ensure borrowers continue to make
payments on time is highly dependent on the
timing of the loan modification. Our research
shows that trigger events such as job loss are
secondary factors compared with the direction of
property prices. While this paper’s sole goal was
to identify the average time a borrower will avoid
default given the current economic situation, a
similar technique can be used to assess how mac-
roeconomic volatility affects borrowers’ abilities
to keep current with the terms of loan modifica-
tion programs.
Sub-Matrix Assumptions
Figure 2
Absorbing Non-absorbing
Absorbing states In O
Non-absorbing
states
R Q
Canonical Form of Transition Matrix
Fundamental Matrix
Figure 3
Figure 4
State Default Current 30+ Delq 60+ Delq 90+ Delq
(Default/60+ Delq) 1 0 0 0 0
(Current/60+ Delq) 0 0.6 0.3 0.1 0
(30+ Delq/60+ Delq) 0 0.5 0.4 0.05 0.05
(60+ Delq/60+ Delq) 0 0.2 0.3 0.4 0.1
(90+ Delq/60+ Delq) 0.3 0.05 0.05 0.1 0.5
State Current 30+ Delq 60+ Delq 90+ Delq
(Current/60+ Delq) 30.2315 18.98148 7.175926 3.333333
(30+ Delq/60+ Delq) 28.287 19.53704 6.898148 3.333333
(60+ Delq/60+ Delq) 26.0648 17.31481 8.009259 3.333333
(90+ Delq/60+ Delq) 11.0648 7.314815 3.009259 3.333333