Lending Club Loan Analysis

• A joint project by fellows of the New York City Data Science Academy to evaluate investment opportunities in Lending Club loans
• The write-up for this project can be found at https://nycdatascience.com/blog/student-works/are-lending-club-notes-a-good-investment/

Setup

• By running import config, a data folder will be created.
• Download accepted_2007_to_2018Q4.csv from https://www.kaggle.com/wordsforthewise/lending-club
• Place the downloaded file in the data folder.
• The code in the Jupyter Notebooks will execute as expected without error.
• Run the Create_Working_DataFrame.ipynb Jupyter Notebook in the data_prep folder to create the working data file.
• You can see an example Jupyter Notebook in EDA/Sample_EDA.ipynb.

Folder Structure

• data: Storage for the data used by EDA and the models
• data_prep: Jupyter Notebooks to manage getting the data and shaping it for analysis
• EDA: Jupyter Notebooks used to explore the data
• lending_club: Python package used by the Jupyter Notebooks
• models: Machine Learning models for predicting defaults
• Project Documentations: Background about the project