Loss Given Default Models

Estimate loss given default

Calculate the loss given default (LGD) using a Regression, Tobit, or Beta model. Calculate the estimated loss reserves using Expected Credit Loss (ECL) calculator.

Functions

expand all

LGD Functions

`fitLGDModel`	Create specified LGD model object type (Since R2021a)
`fryeJacobsLGD`	Compute conditional loss given default (LGD) using Frye-Jacobs model (Since R2024b)
`predict`	Predict loss given default (Since R2021a)
`modelDiscrimination`	Compute AUROC and ROC data (Since R2021a)
`modelDiscriminationPlot`	Plot ROC curve (Since R2021a)
`modelCalibration`	Compute R-square, RMSE, correlation, and sample mean error of predicted and observed LGDs (Since R2023a)
`modelCalibrationPlot`	Scatter plot of predicted and observed LGDs (Since R2023a)

Lifetime Expected Credit Loss (ECL) Calculator

portfolioECL Compute the lifetime ECL at individual or portfolio level (Since R2022a)

Objects

`Regression`	Create `Regression` model object for loss given default (Since R2021a)
`Tobit`	Create `Tobit` model object for loss given default (Since R2021a)
`Beta`	Create `Beta` model object for loss given default (Since R2022b)

Topics

Basic Loss Given Default Model Validation
This example shows how to perform basic model validation on a loss given default (LGD) model by viewing the fitted model, estimated coefficients, and p-values.
Compare Tobit LGD Model to Benchmark Model
This example shows how to compare a Tobit model for loss given default (LGD) against a benchmark model.
Compare Loss Given Default Models Using Cross-Validation
This example shows how to compare loss given default (LGD) models using cross-validation.
Expected Credit Loss Computation
This example shows how to perform expected credit loss (ECL) computations with portfolioECL using simulated loan data, macro scenario data, and an existing lifetime probability of default (PD) model.
Incorporate Macroeconomic Scenario Projections in Loan Portfolio ECL Calculations
This example shows how to generate macroeconomic scenarios and perform expected credit loss (ECL) calculations for a portfolio of loans.
Modeling Probabilities of Default with Cox Proportional Hazards
This example shows how to work with consumer (retail) credit panel data to visualize observed probabilities of default (PDs) at different levels.
Overview of Loss Given Default Models
Loss given default (LGD) is the proportion of a credit that is lost in the event of default.
Create Weighted LGD Model
This example shows how to use the fitLGDModel function to create an LGD model using weighted portfolio data.
Estimate Portfolio-Level LGD with Frye-Jacobs Function
The fryeJacobsLGD function allows you to predict the conditional loss given default (LGD) as a function of the conditional probability of default (PD).

Featured Examples

Model Loss Given Default

Fit different types of models to loss given default (LGD) data. This example demonstrates the following approaches:

Open Live Script

Incorporate Macroeconomic Scenario Projections in Loan Portfolio ECL Calculations

Generate macroeconomic scenarios and perform expected credit loss (ECL) calculations for a portfolio of loans. The workflow in this example shows important computational steps required to estimate provisions for credit losses following regulations such as IFRS 9 or CECL. In practice, the determination of loan provisions is a much more involved operational program requiring the collaboration of multiple departments in an institution. The goal of this example is to show useful computational tools that can support this process.

Open Live Script

Create Weighted LGD Model

Use the fitLGDModel function to create an LGD model using weighted portfolio data. There are many reasons to create a weighted LGD model. For example, consider the scenarios where you want to weight newer data more heavily than older data, or weight certain data points more heavily because they are more relevant to the purposes of a business. In this example, you use LGD portfolio data and assign more weight to investment loans than residential loans.

Open Live Script