AkwasiTp / Prosper-Loan-Dataset-Udacity-Project

An explanatory and exploration analysis of Prosper Loan Dataset provided and supervised by Udacity

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Data Analysis and Visualization of Prosper Loan Dataset

by PRINCE BOADI

Dataset

The Prosper loan dataset contains 113,937 loans with 81 variables on each loan, including loan amount, borrower rate, current loan status, borrower income, and others. During the wrangling phase of my exploration of the data, I removed columns that were not necessary for my analysis, I also changed data types to datetime or categorical as required and made the variables IncomeRange, EmploymentStatus, and LoanStatus ordered categorical data types.

Summary of Findings

  1. The factors that most seemed to affect a loan's outcome was the amount of money borrowed and the interest rate of the loan. Higher interest, high value loans seems to be more likely to be past due. Employed individuals had the highest spread in the data, which makes sense since I assume employed individuals are more likely to apply for and receive loans.

  2. Wedding, Cosmetic procedure and Business loans are likely to be defaulted and In general loans with interest rate higher than 20% are more likely to be defaulted

  3. Borrowers are more likely to pay off their loans with an interest rate of 20% or lower whereas loans with interest rates higher than 25% are more likely to past due and subsequently defaulted

  4. There is a strong negative relationship between borrowers credit score and interest rates on their loans and thus as the borrower's credit score increases, the interest rate decreases.

  5. There is a strong positive relationship between Income range and amount of loans granted. The average amount of loan granted is higher at higher income ranges and lower at lower income ranges. That is to say Borrower's income range affects the amount of loan to be granted to the borrower.

Key Insights for Presentation

  • Wedding, Cosmetic procedure and Business loans are likely to be defaulted and In general loans with interest rate higher than 20% are more likely to be defaulted while Borrowers are more likely to settle their Medical loans, Green loans, Large Purchases and RV

  • The factors that most seemed to affect a loan's outcome was the amount of money borrowed and the interest rate of the loan. Higher interest, high value loans seems to be more likely to be past due and subsequently defaulted

  • Debt Consolidation consitutes 51.2% of listing categories while loans for Home improvement and Business are at 6.5% and 6.3% respectively.

  • Lastly, Borrower's income range have a significant effect on the amount on loan granted. This is depicted with the third visualization as the average loan amounts increases as income range increases.

About

An explanatory and exploration analysis of Prosper Loan Dataset provided and supervised by Udacity


Languages

Language:HTML 71.9%Language:Jupyter Notebook 28.1%