This dataset contains 113937 observations and 81 variables/columns. The focus of this project is to communicate the findings and insights through univariate, bivariate and multivariate Exploration and built a final explanatory visual to support a storytelling. The dataset can be found in the repository of Udacity library here, with feature documentation available here.
In the exploration, I found that Borrower APR was a negatively correlated with the original loan amount.The Borrower APR also decreases with better prosper ratings. The main categories are Debt Consolidations, Auto and Others. The most choose term to pay is 36 months.Better income ranges, and being a home owner gets you better rates.
For the presentation, I focus on just the influence of the most predicable variations leave out most of the intermediate derivations. I start by introducing the borrower APR distribution, followed by monthly loans payments and income ranges, then plot the transformed scatterplot with the stated monthly income and the monthly payments, borrower APR across Prosper rating.
Afterwards, I introduce each of the categorical variables one by one. To start, I use the box plots and violin plots of prosper rating and owning a home across borrower APR.