Description :

In Loan-Marketing business employees are required to call the user's to buy loans of several fields and in several magnitudes. If employees are calling everybody in the network it is also very lengthy and uncertain that most of the customers will buy it. So, there is a very need for a filtering system that segregates the customers who are unlikely to buy loans and the opposite. Loan-Web is visualized and made up on that context.

Goals of the Project :

 1. Ease the job to find the correct vendor/customer.
 2. Reduce time and stress to find out the right customer.
 3. Gaining knowledge from the percentages of likelihood of buying loans and creating campaigns on similar agendas.
 4. Very accurately choosing the right customer.
 5. Reduce asset maintenance expenses as daily calls are getting reduced.

Dataset :

The data has been collected from kaggle Banking Dataset-Marketing Targets. More about the dataset are in this link.

Tech-Stack :

Pyhton environment (v3.8 or higher) equipped with -

       Pyhton Prompt
       Pandas
       Pillow
       Pybase64
       Scikit Learn
       Streamlit

Deployments :

This web app has been successfully deployed on HEROKU. Follow this link to try it online - https://loan-webapp.herokuapp.com/

Or you can fork the whole project in your local machine and try it locally :

Process:

1. Create a Virtual Environment : Tutorial

2. After activating the virtual environment download the dependency libraries through the "requirements.txt" file in Shell.

   $pip install -r requirements.txt
   

3. After installing all the libraries paste the whole repository in that environment base folder and then write a code in Shell.

   $streamlit run loan_web_app.py
   

Interface :

PC interface	Android Interface

HOW to Use :

You can download the use approach.

STAR this repository to keep the developer sane :)

And also follow me on github & kaggle for other Machine Learning / Deep Learning projects.

THANK YOU for visiting :)