Asia Risk Technology Awards 2019
Mean average weighted corporate PD down to 2.24% from 2.61% in Q1 2018
Loss given default estimation: a two-stage model with classification tree-based boosting and support vector logistic regression
In this paper, the authors using a data set composed of five Japanese regional banks, propose an loss given default estimation model using a two-stage model, classification tree-based boosting and support vector regression (SVR).
Italian corporate PD estimates up to 9.12%
Quants propose replacement to existing credit risk measure
Quants propose tail risk-sensitive measure for counterparty credit risk
The potential future loss is proposed as a replacement for PFE
Just 1% to 5% of exposures covered by credit risk mitigants
Supervisors drive banks to seek more corporate default data and cost-effective model improvements
Probabilities of default fall on average across 39 countries
Data highlights the risks posed by economic protectionism, writes David Carruthers of Credit Benchmark
In this paper, the author estimates a two-equation system: one for LGD that incorporates time to recovery as one of the model explanatory variables, and the other for time to recovery using survival models that address data censoring.
Academic aims to address gaps in existing LGD forecast method with two-equation fix
Despite a drop in the bad loan ratio, default estimates continue to rise, writes David Carruthers of Credit Benchmark
EU approach to new credit risk framework must recognise local market structures, say banking experts
Size of task caught some banks unawares, leading to botched home-grown systems or data problems
RBS's total RWAs increase for the first time since 2015
The bank's credit RWAs continue upward trend
This paper reviews the ways of measuring the performance of LGD models that have been previously used in the literature and also suggests some new measures.
A latent variable credit risk model comprising nonlinear dependencies in a sector framework with a stochastically dependent loss given default
This paper proposes a latent variable credit risk model for large loan portfolios. It employs the concept of nested Archimedean copulas to account for both a sector-type dependence structure and a copula-dependent stochastic loss given default (LGD).
Lobbyists confident EU policymakers can be persuaded to implement softer credit risk rules
Lack of convergence allows some banks to benefit from an arbitrage between booking and pricing the adjustment