Predict-The-Status-of-Loan_End-to-End-Project 💻 👨‍🔬

Important notes about the project

This project was built with numerous tools and technologies, this is a summary document. Therefore, if you want to obtain more statistical and computational information see Google Colaboratory, to read about the conclusions found about the project, analyze the Report. Access the application created in Web App.

About this project

In this project, we aim to categorize customers who may or may not receive loans, based on information about the customer's conditions, and many other things.

Applications

The current project can be used to corroborate with your Bank or Insurer to determine the loss that the creditor is exposed to, or to determine the borrower's competence to meet its debt obligations. Although this program is part of my personal portfolio, feel free to use it for studies, repairs and improvements. 🤙

Motivation

This project was developed to be part of my personal portfolio and served both to test my abilities and for my learning, since countless technologies could be used in it. Despite being an end-to-end project, it still needs some future improvements, such as having a larger and more diverse dataset, as well as finding a better efficiency of the model used, which is k-nearest neighbors. 😃

Functionalities

Developed Web APPs:

• Enter Applicant and Co-Applicant details;
• Check an applicant's eligibility from the web application.

Web APP included by Streamlit

• Choose by dark or light theme;
• Rerun;
• Automatically update the app when the underlying code is updated;
• Enable wide mode so the app takes up the entire width of the screen;
• Record a video or audio of the screen;
• Report a bug;
• Get Help;
• About.

Instructions to run and/or compile the code

Initial Requirements

The application is already running and it is not necessary to install anything on your machine, however, if you want to run the application locally, you must install the Python language on your machine. In addition, you must have the libraries listed below on your machine.

Built With

• Pandas 1.4.1;
• Imblearn 0.0;
• pickle-mixin 1.0.2;
• numpy 1.22.2;
• Streamlit 1.6.0;
• scikit-learn 1.0.2;
• seaborn 0.11.2
• Matplotlib 3.2.2.

Hosted In :

• Streamlit

Running the Code

The installations of the libraries are already explained in the links above, but if you want to be in the same versions I do:

pip install scikit-learn==1.0.2

pip install streamlit==1.6.0

pip install numpy==1.22.2

pip install pickle-mixin==1.0.2

pip install pandas==1.4.1

pip install imblearn==0.0

pip install matplotlib==3.2.2

pip install seaborn==0.11.2

done, go to the Deploy folder and type:

streamlit run LoanPredictionWebapp.py

and see the application run on your machine. 😮

Contributing

Criticism, doubts and suggestions feel free to send me:

e-mail: [email protected]

LinkedIn: https://www.linkedin.com/in/marcos-matheus-silva-089699b3/ 🤗

Author

Marcos Matheus de Paiva Silva

Credits

The dataset and business rule can be found on the Kaggle website. The code written in google collaborative was based on the steps of the book Aurelien Geron - hands on machine learning-2019. In addition, this code was developed based on everything I learned from: Jesse E.Agbe, Siddhardhan, Lucas Grassano Lattari, Shashank Kalanithi.

License

This project is licensed under the MIT License - see the file LICENSE for more details.