Mortgage Default Research Articles

Climate Risk Assessment Framework in Real Estate: A Focus on Flooding

Climate change exacerbates flood hazards, resulting in risks to real estate values that should be considered by long-term investors. Flood risk presents two major financial risks: market risk and credit risk. Market risk refers to potential property value loss, and credit risk increases the likelihood of mortgage defaults. However, methods and comprehensive data for quantifying global real estate flood risks are lacking. To address this problem, this paper proposes two flood risk assessment frameworks: the local-oriented approach (LOA) and global-oriented approach (GOA). Two hazard and three vulnerability assessment methods are also introduced to support these frameworks. The LOA vulnerability estimates of regions with complete records are required to support the GOA. Taiwan was selected as an example for the LOA assessment, and the results were used to estimate vulnerability overseas in GOA assessments. The results of case studies for buildings located in four cities in different countries were compared. The proposed framework enables investors and asset owners to globally quantify climate risks in real estate, even when the available data are incomplete. Users can choose the most appropriate approach on the basis of the available data and their tolerance for uncertainty.

Evaluating the impact of demographic characteristics on residential mortgage default risk: Evidence from Lebanon

Purpose: This study aims to examine the relationship between borrower's demographic characteristics and default risk in mortgage loans to help financial institutions develop more effective lending policies. Design/Methodology/Approach: Cross-sectional data were elicited from randomly selected 6743 individual accounts from Lebanese housing banks. This study applied the binary logistic and stepwise regression models to analyze the dataset using the Stata statistical software. Model diagnosis is performed using the Hosmer-Lemeshow goodness of fit test, likelihood ratio test, model accuracy classification table and statistically significant test-ROC curve. Findings: The findings revealed that there is a significant relationship between residential loan default risk and borrower’s marital status, nature of job occupation, job economic sector, job location and loan purpose. The performance of the binary logistic regression analysis demonstrates the overall percentage who is correctly classified is 91.61%. Conclusion: The log odds of default risk for widowed borrowers are about 90 percent higher than those of divorced borrowers and that of self-employed borrowers is about 54 percent higher than that of employed borrowers. Borrowers working in the banking and real estate sectors have lower default rates than borrowers working in other economic sectors. In addition, loans granted for renovation purposes have the lowest default rates compared to loans provided for purchase, under-construction and construction purposes. Practical Implications: The empirical results help financial institutions to have early warning signals in detecting financial distress and to differentiate between a high- and low-risk group of borrowers, helping in the development of tailored risk mitigation strategies and adjusting the lending criteria.

A stochastic loss given default model of Hungarian residential mortgages

AbstractThe paper analyses the Loss Given Default (LGD) rates of residential mortgages, using a model based on stochastic collateral value. The implementation of the model is based on exponential Ornstein-Uhlenbeck processes fitted to the Hungarian regions' house price indices. According to the model results, in case of a mortgage with a 80% loan-to-value ratio at origination, the expected LGD is around 30–40%, depending on the region. The highest LGD rates are estimated for villages, while the lowest rates are expected in Budapest and cities in the middle of the country. The range of the regional differences can reach 7 percentage points. According to the LGD Risk index based on the aggregated model, the LGD risk profile of recently issued mortgages has improved significantly since 2009 in Hungary.Due to the strong negative relation between the house prices and mortgage default rates, the expected return on defaulted collateral value tends to be low. The results could be relevant for credit institutions in their mortgage origination decisions and enhance analysis of lending processes and the associated risks.

Climate stress testing for mortgage default probability

Extreme natural disasters, such as tropical cyclones, have a low probability of materialising, but a high social and economic impact, including spillover to financial institutions. We propose a framework for performing a climate-stress testing exercise for the default probability of mortgage loans. We estimated a dynamic credit scoring model based on survival analysis with a relative damage index built using the wind speed of tropical cyclones. We considered scenarios involving tropical cyclone wind speeds with different return periods. We analyse a portfolio of approximately 190,000 mortgage loans granted in Louisiana, one of the US states most affected by tropical cyclones. Our findings suggest that coastline areas are most exposed to severe damage from tropical cyclones. If the geographical area is exposed to an event with a very large return period of 1-in-1,000 years, the probability of default increases by approximately nine percentage points compared to a baseline scenario in the absence of tropical cyclones. However, this finding was mitigated by the insurance coverage. This percentage increases to almost 20 percent in the absence of insurance coverage.

Predicting Mortgage Loan Defaults Using Machine Learning Techniques

Mortgage default prediction is always on the table for financial institutions. Banks are interested in provision planning, while regulators monitor systemic risk, which this sector may possess. This research is focused on predicting defaults on a one-year horizon using data from the Ukrainian credit registry applying machine-learning methods. This research is useful for not only academia but also policymakers since it helps to assess the need for implementation of macroprudential instruments. We tested two data balancing techniques: weighting the original sample and synthetic minority oversampling technique and compared the results. It was found that random forest and extreme gradient-boosting decision trees are better classifiers regarding both accuracy and precision. These models provided an essential balance between actual default precision and minimizing false defaults. We also tested neural networks, linear discriminant analysis, support vector machines with linear kernels, and decision trees, but they showed similar results to logistic regression. The result suggested that real gross domestic product (GDP) growth and debt-service-to-income ratio (DSTI) were good predictors of default. This means that a realistic GDP forecast as well as a proper assessment of the borrower’s DSTI through the loan history can predict default on a one-year horizon. Adding other variables such as the borrower’s age and loan interest rate can also be beneficial. However, the residual maturity of mortgage loans does not contribute to default probability, which means that banks should treat both new borrowers equally and those who nearly repaid the loan.

Evaluating the Impact of Borrower Characteristics, Loan Specific Parameters, and Property Conditions on Mortgage Default Risk

Evaluating the Impact of Borrower Characteristics, Loan Specific Parameters, and Property Conditions on Mortgage Default Risk

Az energiahatékonyság szerepe a jelzáloghitelek csődvalószínűségében és a tőkekövetelmények meghatározásában

Our study aims to contribute to the literature on mortgage defaults and energy efficiency of the collateral. The risk differentials of green mortgages are highly relevant from a policy perspective, especially for the determination of capital requirements that are traditionally risk-based. As a theoretical background, we describe the channels through which the energy efficiency of households can reduce the probability of default. Within this decomposition, we distinguish between the effects of disposable income, financial literacy, the effect of wealth and the effect of the real estate collateral. We analyze the effect of the increased disposable income of energy-efficient households on the probability of default of mortgage loans in Hungary, where the central bank introduced a preferential capital requirement program for green mortgage loans. The primary outcome of energy efficiency gains is savings in energy units. In our study, we present the process of determining the theoretically and measurably achievable energy savings resulting from the limiting mechanisms. Due to the changing energy prices, we will not convert the energy measurement units into currency. The primary goal of our study is to present the methodology of how the results of energy savings can be included in credit risk.

Prediction of creditworthiness of borrowers for Mortgage Lending using Random Forest Algorithm

The assessment of creditworthiness is a critical task in mortgage lending which directly influences the risk management strategies of financial institutions. The paper presents the development and implementation of a credit scoring model tailored for mortgage lending, using the Random Forest algorithm. Utilizing a comprehensive dataset comprising borrower information, credit history, and financial indicators, the model predicts the likelihood of mortgage default or delinquency. The Random Forest classifier is chosen after comparing its performance with several other machine learning models, including Logistic Regression, Decision Tree, K-Nearest Neighbors, Naïve Bayes, and Support Vector Machine. The chosen model demonstrated an accuracy of 85.22 %, indicating robust performance in distinguishing between credit-worthy and non-credit-worthy applicants. This model aids in risk assessment by minimizing false positives and negatives, thereby optimizing the mortgage lending process. Furthermore, the model’s deployment through a Streamlit application automates the mortgage application process, enhancing efficiency and reducing operational costs. The findings underscore the potential of machine learning algorithms to revolutionize credit risk assessment in mortgage lending, providing financial institutions with a reliable tool for making informed lending decisions. Key Words: Credit Scoring, Mortgage Lending, Random Forest Algorithm, Risk Assessment

Mortgage Status and Financial Stress: Do Home Equity Loans, Negative Home Equity, and Mortgage Default Matter?

A home is often the largest asset held by U.S. households. If home equity accumulation is slowed through acquiring a home equity loan, threatened through mortgage default, or undermined through the occurrence of negative home equity, homeowners may experience increased financial stress. This study used the 2018 National Financial Capability Study to assess the relationship between three mortgage statuses (having a home equity loan, negative home equity, or mortgage default) and financial stress among nonretiree mortgage holders (N= 5,058). Financial stress was measured by an index of financial difficulty perceptions. Findings revealed that negative home equity is related to greater levels of financial stress than mortgage default or having a home equity loan. Additionally, experiencing a large drop in income intensified the positive relationship between negative home equity and the financial stress index. These findings suggest that conditions seemingly outside the control of homeowners may influence their financial stress perceptions.

Climate risk in mortgage markets: Evidence from Hurricanes Harvey and Irma

AbstractUsing the Credit Risk Transfers (CRTs) issued by Fannie Mae and Freddie Mac, we study how, absent government intervention, mortgage markets would price hurricane risk. Currently, such risk is priced equally across locations even if it is location‐specific. We hand collect a novel and detailed database to exploit CRTs' heterogeneous exposure to Hurricanes Harvey and Irma. Using a diff‐in‐diff specification, we estimate the reaction of private investors to hurricane risk. We use the previous results to calibrate a model of mortgage lending. We simulate hurricane frequencies and mortgage default probabilities in each US county to derive the market price of mortgage credit risk, that is, the implied guarantee fees (g‐fees). Market‐implied g‐fees in counties most exposed to hurricanes would be 70% higher than inland counties.

Mortgage Default, Financial Disintermediation and Macroprudential Policies

Mortgage Default, Financial Disintermediation and Macroprudential Policies

Climate Stress Testing for Mortgage Default Probability

Climate Stress Testing for Mortgage Default Probability

Applying Machine Learning Techniques to Evaluate Climate-Related Risks in Real Estate Mortgage Valuations

Facing the escalating effects of climate change, the real estate industry faces risks from physical perils and shifting towards a low-carbon economic model. These risks have substantial consequences for the assessment and effectiveness of real estate mortgage portfolios. Conventional approaches to evaluating mortgage risk frequently fail to capture the intricate, non-linear connections between climate variables and loan results. In this paper, we present a new machine-learning framework that aims to quantify climate-related risks in real estate finance. We utilize neural networks and gradient-boosting algorithms to forecast the likelihood of mortgage defaults and the potential loss resulting from defaults in different climate stress scenarios. A robust and forwardlooking risk assessment is developed by integrating property-level exposure data, loan characteristics, and macroeconomic indicators. The empirical findings prove that our models perform superior to conventional econometric methods regarding predictive precision and computational effectiveness. The framework offers a robust instrument for investors, lenders, and regulators who aim to effectively address climate risks and enhance their ability to withstand and adapt to an unpredictable future.

The Effect of Broker–Borrower Interaction on Mortgage Defaults

This research proxy uses the distance between brokers and borrowers to explore the interaction between brokers who provide consulting services to prospective property buyers. Meanwhile, the view from the banking side is assessing the risk profile of prospective mortgage borrowers. The research data collection is information on mortgage borrowers from Private Banks in Surabaya branches from the period 2015 - 2020 who used the help of real estate agents when buying a house and collected 1295 transactions. Data processing using probit regression. The test results show that the interaction between brokers and borrowers using distance as a proxy has no significant impact on mortgage defaults. Borrower interest rates raised by the company showed a substantial negative relationship with mortgage default. The study also reveals that borrower income has no impact on mortgage default. The managerial implication for banks is to determine the strategy of cooperation with property brokers to increase mortgage funding.

Impacts of extreme weather events on mortgage risks and their evolution under climate change: A case study on Florida

We develop an additive Cox proportional hazard model with time-varying covariates, including spatio-temporal characteristics of weather events, to study the impact of weather extremes (heavy rains and tropical cyclones) on the probability of mortgage default and prepayment. We compare the survival model with a flexible logistic model and an extreme gradient boosting algorithm. We estimate the models on a portfolio of mortgages in Florida, consisting of 69,046 loans and 3,707,831 loan-month observations with localization data at the five-digit ZIP code level. We find a statistically significant and non-linear impact of tropical cyclone intensity on default as well as a significant impact of heavy rains in areas with large exposure to flood risks. These findings confirm existing results in the literature and also provide estimates of the impact of the extreme event characteristics on mortgage risk, e.g. the impact of tropical cyclones on default more than doubles in magnitude when moving from a hurricane of category two to a hurricane of category three or more. We build on the identified effect of exposure to flood risk (in interaction with heavy rainfall) on mortgage default to perform a scenario analysis of the future impacts of climate change using the First Street flood model, which provides projections of exposure to floods in 2050 under RCP 4.5. We find a systematic increase in risk under climate change that can vary based on the scenario of extreme events considered. Climate-adjusted credit risk allows risk managers to better evaluate the impact of climate-related risks on mortgage portfolios.

What Triggers Mortgage Default? New Evidence from Linked Administrative and Survey Data

Abstract Why do homeowners default on mortgages? This paper studies the question using a survey specifically designed for the purpose, with a sample drawn from (and matched to) very rich administrative data. I find that a wide variety of typically-unobserved liquidity shocks together trigger nearly all defaults, so “strategic” default with no liquidity trigger is much less common than it usually appears. Conversely, even in this uniquely rich data I find that many foreclosures are not triggered by negative home equity, contrary to the predictions of almost every model in the literature.

Macroprudential Policy, Mortgage Cycles, and Distributional Effects: Evidence from the United Kingdom

Abstract We analyze the distributional effects of macroprudential policy on mortgage cycles by exploiting the U.K. mortgage register and a 2014 15% limit imposed on lenders’ high loan-to-income (LTI) mortgages. Constrained lenders issue fewer and more expensive high-LTI mortgages, with stronger effects on low-income borrowers. Unconstrained lenders strongly substitute high-LTI loans in local areas with higher constrained lender presence, but not high-LTI loans to low-income borrowers—consistent with adverse selection problems—implying lower overall credit to low-income borrowers. Consistently, policy-affected areas experience lower house price growth postregulation and, following the Brexit referendum (negative aggregate shock), better house price growth and lower mortgage defaults for low-income borrowers.

The Anatomy of Mortgage Default Using Shape-Constrained Explainable Machine Learning Model

The Anatomy of Mortgage Default Using Shape-Constrained Explainable Machine Learning Model

Incorporating Climate Risk into Credit Risk Modeling: An Application in Housing Finance

This paper examines the integration of climate risks into structural credit risk models. We focus on applications in housing finance and argue that mortgage defaults due to climate disasters have different statistical features than default due to household-specific reasons. We propose two models incorporating climate risk based on two separate default definitions. The first focuses on default as a response to a decrease in home value, and the second defines default as a consequence of missed mortgage payments. Using mortgage performance data during Hurricane Harvey, we conduct an empirical study whose results suggest that climate events are potentially another source of undiversifiable credit risk affecting homeowners’ ability to make contractual monthly payments. We also show that incorporating this climate-specific default process may capture additional uncertainty in default probability assessments.

Serious Mortgage Arrears among Immigrant Descendant and Native Participants in a Low-Income Public Starter Mortgage Program: Evidence from Norway

Although low-income homeownership programs serving vulnerable families at the lower end of the income distribution have been the focus of housing policy in many countries over the past 50 years, little is known about the post-origination experiences of immigrant families participating in these programs. Notably absent from the extant literature are studies examining the sustainability of homeownership among immigrant homebuyers and their susceptibility to falling behind on payments and experiencing mortgage defaults, evictions, or short sales. Utilizing data from 8263 families participating in Norway’s Starter Mortgage Program (Startlån) during the first three calendar years after mortgage origination, we examine the extent to which serious mortgage arrears varies by immigrant background. Two primary questions shape our research: (1) What is the incidence of serious mortgage arrears among Western, Eastern European, and non-Western immigrant homeowners relative to ethnic Norwegians participating in a public low-income homeownership program? and (2) What pre- and post-origination characteristics of applicants and households, mortgage terms at the time of origination, and experiences of household financial vulnerability or economic shocks predict heterogeneity in serious mortgage arrears by immigrant backgrounds? We found that 6.1% of ethnic Norwegian, 6.2% of Western, 4.9% of non-Western, and 3.2% of Eastern European immigrant homeowners participating in the Starter Mortgage Program were in serious mortgage arrears at least once during the first three calendar years after mortgage origination. Results from our negative binomial regression analyses suggest that program participants who were sole owners, with larger families, and higher debt were more likely to experience serious mortgage arrears; these effects were accentuated for ethnic Norwegians. Additionally, mortgage terms at the time of origination produced differential effects by immigrant background. Compared to Western and Eastern European immigrant homeowners, ethnic Norwegians were more likely to have experienced serious mortgage arrears if they purchased a single-family home, had larger LTV and DTI ratios, or if the Startlån share of their mortgages was higher. Non-Western immigrant mortgagors were more likely to make late mortgage payments if they had larger LTV ratios, interest-only mortgage servicing, or if they were more reliant on Startlån funds to finance their mortgages; however, this risk was reduced if they had fixed-rate mortgages. Financial vulnerability in terms of higher debt or fewer assets also increased the risk of serious mortgage arrears for ethnic Norwegians and non-Western immigrant homeowners, while increases in real wealth reduced that risk for all immigrant mortgagor groups.