Code Monkey home page Code Monkey logo

lendingclub-rate-of-return-prediction-using-socioeconomic-factors's Introduction

Lending Club Rate of Return Prediction using Socio-Economic Factors and SMOTE sampling

Concept:

A traditional banking counterpart, Lending Club is an online market place for borrowers and lenders and has become a major player in the peer-to-peer lending business with an average rate of return between 3% and 8% per year. Lenders, before committing their money, carefully investigate a multitude of associated risks such as -borrower defaults -liquidity risk -poor loan diversification, etc. But for a steady return, lenders are advised to diversify their portfolio by investing in different loans with different rate of interest. Most of these modeling techniques utilize collected borrower’s personal, professional and credit information. This is crucial for non-traditional banks such as Lending Club because to maintain a low-interest rate and expand their customer base, they need to accurately identify and decline potential defaulters.

One factor that is rarely assessed over the period is the borrower’s zip-code specific socio-economic indicators such as no. of workers, workers in different industry & occupation, below poverty line families, unemployment rate, etc. in a location. In the latest study, median household income for individual zip-code was used to predict loan default and has reported an increase in the accuracy. This study attempts to strategize investment portfolio by two-stage scoring approach, which is an integration of classification of default loans and prediction of annualized rate of return (ARR) using zip-code specific socio-economic indicators from American Fact Finder and loan history data from Lending Club. More specifically, this study will explore re-sampling techniques such as random under-sampling, random over-sampling and SMOTE to further increase the accuracy in prediction using SAS® Enterprise Miner™, 7 SAS® Enterprise Guide®, and Python 3. The numerical study indicates the predicted return and portfolio size is more realistic and better than existing investment methods such as bonds, savings accounts & Prosper Lending

Process Flow:

Process_Flow

lendingclub-rate-of-return-prediction-using-socioeconomic-factors's People

Contributors

priyabratathatoi avatar

Stargazers

 avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.