https://github.com/kshitijshrivastava1903/neural_network_analysis_on_lending_club-dataset

Used tensorflow's neural network model to predict whether or not a person pays back a loan on the basis of his historical data and personal details of 3.9 lakh people like interest rate, employment details, address, etc.
https://github.com/kshitijshrivastava1903/neural_network_analysis_on_lending_club-dataset

deep-learning dropout-keras earlystopping keras-tensorflow matplotlib-pyplot neural-networks numpy pandas seaborn tensorflow-models

Last synced: 13 days ago
JSON representation

Used tensorflow's neural network model to predict whether or not a person pays back a loan on the basis of his historical data and personal details of 3.9 lakh people like interest rate, employment details, address, etc.

• Host: GitHub
• URL: https://github.com/kshitijshrivastava1903/neural_network_analysis_on_lending_club-dataset
• Owner: kshitijshrivastava1903
• Created: 2020-06-17T17:54:12.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2020-06-18T06:37:46.000Z (over 4 years ago)
• Last Synced: 2024-11-03T06:42:31.346Z (2 months ago)
• Topics: deep-learning, dropout-keras, earlystopping, keras-tensorflow, matplotlib-pyplot, neural-networks, numpy, pandas, seaborn, tensorflow-models
• Language: Jupyter Notebook
• Homepage:
• Size: 284 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Predict whether a person will pay back your loan on the basis of his/her historical data.

Used tensorflow's neural network model to predict whether or not a person pays back a loan on the basis of his historical data and personal details of around 4 lakh people, like employment details, address, loan amount, etc.

LENDING CLUB is a US peer-to-peer lending company, headquartered in San Francisco, California. It was the first peer-to-peer lender to register its offerings as securities with the Securities and Exchange Commission (SEC), and to offer loan trading on a secondary market. LendingClub is the world's largest peer-to-peer lending platform.

Our Goal:

Given historical data on loans given out with information on whether or not the borrower defaulted (charge-off), I built a model that can predict wether or nor a borrower will pay back their loan. This way in the future when we get a new potential customer we can assess whether or not they are likely to pay back the loan.

Done a lot of exploratory data analysis, feature engineering, data cleaning and created a dense neural network using dropout 

layers, and plotted out the loss on training data and testing data to prevent overfitting of data and finding optimal solution.