To build a good model, it is important to use high quality data. For the purpose of this course, we will use the loan data available From LendingClub's website. LendingClub is a US peer-to-peer lending company which matches borrowers with investors willing to fund their loans.

LendingClub provides rich datasets a which are available to public for analysis and can be downloaded from the following link:

https://www.lendingclub.com/info/download-data.action

We have downloaded the data for 2016 Quarter 1, which contains complete loan data for all loans issued during Q1 2016, including the current loan status (Current, Late, Fully Paid, etc.) and latest payment information. When you download the data file (csv), the original file is named LoanStats_2016Q1.csv. We have renamed the file to loan_data_2017.csv for simplicity. (Note: This is a big file - 109MB)

Before we begin building our model, our first step would be to explore the data, understand more about it, and also transform the data where necessary so that it is suitable for analysis. We have intentionally chosen to demonstrate things here starting with the raw data file in order to emulate a real model building scenario.

Download the data file either directly from the LendingClub website or from the link below:

Once the file is downloaded, move it to your R working directory. This tutorial is creating on a MacBook, so the paths are set according the MacBook’s folder structure.

> setwd("~/Dropbox/Finance Train/Courses/Credit_Risk_Modelling_R")

The above command sets the given folder as the working directory where I have stored the data file.