Credit Risk Modeling in R

This course is part of these tracks:

Quantitative Analyst with R

Lore Dirick

Data Scientist at DataCamp

Lore is a data scientist at DataCamp. She obtained her PhD in Business Economics and Statistics at KU Leuven, Belgium. During her PhD, she collaborated with several banks working on advanced methods for the analysis of credit risk data. At DataCamp, she is in charge of building out the Applied Finance curriculum.

Prerequisites

Datasets

Course Description

This hands-on-course with real-life credit data will teach you how to model credit risk by using logistic regression and decision trees in R.

Modeling credit risk for both personal and company loans is of major importance for banks. The probability that a debtor will default is a key component in getting to a measure for credit risk. While other models will be introduced in this course as well, you will learn about two model types that are often used in the credit scoring context; logistic regression and decision trees. You will learn how to use them in this particular context, and how these models are evaluated by banks.

1
Introduction and data preprocessing
Free

This chapter begins with a general introduction to credit risk models. We'll explore a real-life data set, then preprocess the data set such that it's in the appropriate format before applying the credit risk models.
View Chapter Details Play Chapter Now
Logistic regression

Logistic regression is still a widely used method in credit risk modeling. In this chapter, you will learn how to apply logistic regression models on credit data in R.
View Chapter Details Play Chapter Now
Decision trees

Classification trees are another popular method in the world of credit risk modeling. In this chapter, you will learn how to build classification trees using credit data in R.
View Chapter Details Play Chapter Now
Evaluating a credit risk model

In this chapter, you'll learn how you can evaluate and compare the results obtained through several credit risk models.
View Chapter Details Play Chapter Now

Courses

Tracks

Instructors

Credit Risk Modeling in R

Lore Dirick

Prerequisites

Datasets

Course Description

Introduction and data preprocessing

Introduction

Exploring the credit data

Interpreting a CrossTable()

Histograms and outliers

Histograms

Outliers

Missing data and coarse classification

Deleting missing data

Replacing missing data

Keeping missing data

Data splitting and confusion matrices

Splitting the data set

Creating a confusion matrix

Logistic regression

Logistic regression model: introduction

Basic logistic regression

Interpreting the odds for a categorical variable

Multiple variables in a logistic regression model

Interpreting significance levels

Logistic regression model: predicting the probability of default

Predicting the probability of default

Making more discriminative models

Evaluating the logistic regression model result

Specifying a cut-off

Comparing two cut-offs

Wrap-up and remarks

Comparing link functions for a given cut-off

Decision trees

What is a decision tree?

Computing the gain for a tree

Changing one Gini...

Building decision trees using the rpart package

Undersampling the training set

Changing the prior probabilities

Including a loss matrix

Pruning the decision tree

Pruning the tree with changed prior probabilities

Pruning the tree with the loss matrix

Other tree options and confusion matrices

One final tree using more options

Confusion matrices and accuracy of our final trees

Optimizing the accuracy

Evaluating a credit risk model

Finding the right cut-off: the strategy curve

Computing a bad rate given a fixed acceptance rate

The strategy table and strategy curve

To tree or not to tree?

The ROC-curve

ROC-curves for comparison of logistic regression models

ROC-curves for comparison of tree-based models

Input selection based on the AUC

Another round of pruning based on AUC

Best of four

Further model reduction?

Course wrap-up