An Analysis and Risk Modeling on Mortgage Payment Defaults

SSRN Electronic Journal, 2012

This study examines the performance of logistic regression in predicting probability of default using data from a microfinance company. A logistic regression analysis was conducted to predict default status of loan beneficiaries using 90 sampled beneficiaries for model building and 30 out of sample beneficiaries for prediction. Age, marital status, gender number of years of education, number of years in business and base capital were used as predictors. The predictors that were significant in the model were marital status, number of years in business and base capital. The explained variability in the response variable in the logistic regression was very weak.

Working Papers, 2004

This paper explores the relationship between consumer credit clients' payment performance ie credit default risk and some demographic and financial variables. Data to examine this relationship is obtained from the customer records of a private bank in Turkey. A logistic binary ...

2016

Credit scoring is an application of financial risk forecasting to consumer lending. In this study, statistical analysis is applied to credit scoring data from a financial institution to evaluate the default risk of consumer loans. The default risk was found to be influenced by the spread, the age of the consumer, the number of credit cards owned by the consumer. A lower spread, a higher number of credit cards and a younger age of the borrower are factors that decrease the risk of default. Clients receiving the salary in the same banking institution of the loan have less chances of default than clients receiving their salary in another institution. We also found that clients in the lowest income tax echelon have more propensity to default.

2013

This study investigates the possible effects of macroeconomic factors on mortgage credit default risk in Turkey. In our literature review, the main macroeconomic factors are to be found as house prices, unemployment, interest rates and inflation. Although default and many macroeconomic factros are found to be related, we believe that the pay off performance of mortgage credits is strong among other consumer credits. A positive performance in macroeconomic conditions affect mortgage pay offs positively, whereas worsening macroeconomic conditions do not affect mortgage pay offs that negatively. We employed regression analysis to evaluate the effects of various macroeconomic factors on both mortgage default rates and total consumer default rates in Turkey in line with the literature. We found that previous defaults, house prices, interest rates and stock market movements have significant effect on defaults. The house prices return found to be the most effective while we used difference of previous defaults and difference of interest rates on mortgage credits defaults analysis. For consumer credits defaults analysis, the return of stock market index, difference of previous defaults and government interest rates are considered in the analysis. v

ECONOMETRICS, 2018

Default risk assessment is crucial in the banking activity. Different models were developed in the literature using the discriminant analysis, logistic regression and data mining techniques. In this paper the logistic regression was applied to verify models proposed by R. Jagiełło for different sectors. As an alternative, the logistic regression model with the nominal variable SECTOR was applied on the pooled sample of enterprises. The dynamic approach using the Cox regression survival model was estimated. Including the nominal variable SECTOR only slightly increases the predictive power of the model (in the case of "defaults"). The predictive power of the Cox regression model is lower, the only advantage is the higher accuracy classification in the case of "defaulted" enterprises.

VIDYA - A JOURNAL OF GUJARAT UNIVERSITY

Credit risk, also known as default risk, is the likelihood of a corporation losing money if a business partner defaults. If the liabilities are not met under the terms of the contract, the firm may default, resulting in the loss of the company. There is no clear way to distinguish between organizations that will default and those that will not prior to default. We can only make probabilistic estimations of the risk of default at best. There are two types of credit risk default models in this regard: structural and reduced form models. Structural models are used to calculate the likelihood of a company defaulting based on its assets and liabilities. If the market worth of a company's assets is less than the debt it owes, it will default. Reduced form models often assume an external cause of default, such as a Poisson jump process, which is driven by a stochastic process. They model default as a random event with no regard for the balance sheet of the company. This paper provides ...

SSRN Electronic Journal, 2007

This paper presents a simple version of the application of option based pricing models to mortgage credit risk. The approach is based on the notion that default can be viewed as exercising a put option, and that the place to look in modelling default is the extent to which the option is in the money (the extent to which the borrower has negative equity in the property) and, given that, the incentive, e.g., a trigger event and inability to withstand it, to exercise the option. The main focus is on how the probability of default can be estimated and how the default risk can be priced. The analysis considers both "first principles" and specific analysis about U. S. default experience.

The Basel II Accord offers banks the opportunity to estimate Loss Given Default (LGD) if they wish to calculate their own value for the capital required to cover credit losses in extreme circumstances. This paper will analyze the various methods of modeling LGD and will provide an alternative estimate of LGD using Merton's model for the valuation of assets. Four components will be developed in this document: estimation of the minimum value that could have a financial asset, estimation of the loss given default LGD, development of a practical component, and finally validation of the proposed model. JEL classification numbers: G17, G24, G32

The Journal of Real Estate Finance and Economics, 2005

We apply the powerful, flexible, and computationally efficient nonparametric Classification and Regression Trees (CART) algorithm to analyze real estate mortgage data. CART is particularly appropriate for our data set because of its strengths in dealing with large data sets, high dimensionality, mixed data types, missing data, different relationships between variables in different parts of the measurement space, and outliers. Moreover, CART is intuitive and easy to interpret and implement. We discuss the pros and cons of CART in relation to traditional methods such as linear logistic regression, nonparametric additive logistic regression, discriminant analysis, partial least squares classification, and neural networks, with particular emphasis on real estate. We use CART to produce the first academic study of Israeli mortgage default data. We find that borrowers' features, rather than mortgage contract features, are the strongest predictors of default if accepting "bad" borrowers is more costly than rejecting "good" ones. If the costs are equal, mortgage features are used as well. The higher (lower) the ratio of misclassification costs of bad risks versus good ones, the lower (higher) are the resulting misclassification rates of bad risks and the higher (lower) are the misclassification rates of good ones. This is consistent with real-world rejection of good risks in an attempt to avoid bad ones.

This study provides comprehensive default probability estimation for automobile loans. An extension of the Cox Proportional Hazards model proposed by Vaida and Xu (2000) by incorporating random-effects was used to handle clustered survival data. The estimation procedure was used in the context of credit scoring incorporating term of the financial obligation as a cluster-specific random component. Balancing was performed due to the highly imbalanced nature of the data. Under-sampling was performed to make the censored class less dominant. The estimated model captured dimensions of automobile loan borrowers such as characteristics and payment behavior. Borrowers tend to exhibit correlation in default incidence within the same loan term, but different propensity to default was observed across loan terms. Models estimated using the balanced data exhibit better predictive performance relative to the model estimated using the imbalanced data. The final model can be a basis for developing collection strategies and loan loss provisioning for effective loan management.

Research Journal of Finance and Accounting, 2014

This paper aims at developing a credit scoring model that can best be used to ascertain the credit score and predict probability of default of firms seeking credit. The study subsequently aspires to find the financial ratios that can best be used to successfully construct the credit score and predict default risk. To achieve these purposes, the paper applied the logit model. Performance of the model was assessed using the percentage correctly classified (PCC) and the area under the receiver operating characteristic curve (AUC). The results show that the logit model yield very good performance rate for credit scoring and risk assessment. Further empirical evidence indicates that ratios bordering on: interest coverage, liquidity, activity, and firm size are those that can be significantly helpful in scoring credit applicants and assessing credit risk. Practically, the model can aid in reducing the time spent on evaluating credit applicants, and can give an exact default-risk intensity of each firm subjected to the model as well as serve as an early warning system. The multiplier effect will be a significant improvement in loan portfolio quality of the model user which is in accordance with the Basel II framework.

The main idea of this paper is to study theoretically the different ones from the credit portfolio models mainly two models: the macro-factors models and the actuarial models. There are currently three types of models to consider the risk of credit: the structural models also defined by the models of the value of the firm, the intensity models and the econometric models. In the financial literature, the development of those three types of models is based on a theoretical basis developed by many researchers mainly in the last decade of the twentieth century. The evolution of their default frequencies and the size of the loan portfolio are modeled as functions of macroeconomic and microeconomic conditions as well as unobservable credit risk factors, which explained by other factors. We developed two sections to explain the different characteristics of the macro-factors models and the CreditRisk+ models.

2013

Mortgage credit has become one of the most important, financial obligations of the Portuguese families, but on the other hand, this type of credit has been able to boost some economic sectors in Portugal. It is important to study default in the mortgage credit due to its impact on families, and also on the banking and real estate market. The aim of this work is twofold. Firstly, using an option pricing model, I propose to price the put option and analyze if the house owners exercised default due to a high put price. Secondly, I shall use a Vector Autoregressive model with macroeconomic variables to analyze if they affect the current rate of default when the put option is not valuable enough to be exercised. The main result suggests that the investor's put option was not valuable enough to justify the exercising of his/her default option. Studying the proposed macroeconomic variables led me to the result that GDP, Net Savings, Unemployment and Real estate Volatility have negative impacts on Credit Default.

A. M. Karminsky et al. (eds.), Risk Assessment and Financial Regulation in Emerging Markets’ Banking, Advanced Studies in Emerging Markets Finance, 2021

This chapter proposes an approach to decompose the RR/LGD model development process with two stages, specifically, for the RR/LGD rating model, and to calibrate the model using a linear form that minimizes residual risk. The residual risk in the recovery of defaulted debts is determined by the high uncertainty of the recovery level according to its average expected level. Such residual risk should be considered in the capital requirements for unexpected losses in the loan portfolio. This paper considers a simple residual risk model defined by one parameter. By developing an optimal RR/LGD model, it is proposed to use a residual risk metric. This metric gives the final formula for calibrating the LGD model, which is proposed for the linear model. Residual risk parameters are calculated for RR/LGD models for several open data sources for developed and developing markets. An implied method for updating the RR/LGD model is constructed with a correction for incomplete recovery through the recovery curve, which is built on the training sets. Based on the recovery curve, a recovery indicator is proposed which is useful for monitoring and collecting payments. The given recommendations are important for validating the parameters of RR/LGD model.