Exploratory Data Analysis in R using loan data from peer-to-peer lending platform Prosper.

Click here to view the Prosper Loans EDA Report.

Prosper is a peer-to-peer lending platform that aims to connect people who need money with those who have money to invest. In this Exploratory Data Analysis, I explore a Prosper dataset containing loan information for over a 100,000 people between the years 2006 and 2013.

I first sifted through the dataset, which has 82 variables, and roughly thought about which variables I was interested in exploring and which were outside the domain of my exploration. I first planned on making a subset of the data, but instead opted for using the entire dataset in case I got any new ideas midway through my exploration.

I wanted my EDA to have a purpose, to show to those who are interested the facts about the loan data. In peer-to-peer lending, there are three main stakeholders: borrowers, lenders, and the organization itself. I have decided that I want to focus on Prosper as a stakeholder, and have designed this exploration with their interests in mind (I have not ignored the borrowers and lenders, however, and there's a lot of revelations for them as well).

The exploration is divided into 3 analytical segments in increasing order of complexity: Univariate Plots, Bivariate Plots, and Multivariate Plots, as well as a Reflection segment at the end that summarizes my experience and thoughts throughout this EDA.

There are two files provided - the HTML (knitted) report and the original RMD file.