Skip to content

ML-based web application for finding out eligibility for Loan

Notifications You must be signed in to change notification settings

JackJJCodes/LoanPred

Repository files navigation

LoanPred

A Flask-based web application for people to find out if they are eligible for a loan or not.

Contributors:

This project was made as submission for a college course. It was made by me and my good friend/coder Nimesh Srivastava. Link to his GitHub profile is here.

Motivation:

Banks and Lending Instituitions have been around almost since the dawn of time. Well, OK, not that long. But people have been borrowing and lending money for centuries. If you look at it in its simplest terms, someone wants to borrow money, someone has money they wish to lend. You take out a loan from the lender, terms are discussed such as how long you will be paying the loan back, and at what rate of interest.

Although, the process of getting a loan is very tedious. People need to submit their application form, then wait for 1-2 days till the loaning committee accepts the application. then, we get the loan.

To automate this process, we have created a web application, in which the user has to just enter the required fields, and within seconds, he/she will get to know if they are eligible for a loan or not.

Tech Stack Used:

Algorithms Used:

I have tried using many algorithms for this problem, but Random Forest seemed to work the best for me. It gave me an accuracy of nearly 80%.
If you want an in-depth explanation of Random Forest, feel free to check out this article.

Screenshots:






Issues:

  1. Adding recommendation feature, so that a user would get the name of the banks willing to give them a loan.

To run this on your machine:

  1. Make sure you have Python3, Flask installed.
  2. In your terminal, cd to the folder you got this project in, and type python run app.py
  3. And voila!!

About

ML-based web application for finding out eligibility for Loan

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published