Discontinuity in Relative Credit Losses: Evidence from Defaults on Government-Insured Residential Mortgages

Abstract

This paper investigates the distribution of relative credit losses given mortgage default for loans provided by a major government-sponsored creditor in a local area. We use borrower's individual and loan-level data on residential mortgages originated in the period 2008-2012. Our numerical analysis indicates that mortgages bunching at certain Loan-to-Value ratios (LTV) led to a discontinuity in relative credit loss given mortgage default. Through regression analysis, we demonstrate discrete jumps in the approximated historical credit losses generated by loans with a high LTV ratios and find thresholds allowing the segmentation of loans according their credit risk. In addition, our results suggest that mortgage insurance is a potentially valuable instrument for compensation for expected loss in certain risk segments.

Consumer Bankruptcy Prediction Using Balanced and Imbalanced Data

“…Debt repayment behaviors or a consequence of e.g., having too many loans and inadequate management of the household budget, such as late repayment may constitute an early warning of impending bankruptcy (Moorman and Garasky 2008;Himmelstein et al 2005). Lozinskaia et al (2016) noted that the accumulation of mortgage loans depending on the level of loan amount and the value of the asset led to a discontinuity in the relative credit loss in the event of mortgage default. Alfaro and Gallardo (2012) also drew attention to the type of defaulted liabilities.…”