theiturhs commented 1 month ago

Pull Request for DL-Simplified 💡

Issue Title : [Model Enhancement and Feature Addition]: Bank Loan Approval Prediction with Web App

Info about the related issue : The aim is to enhance the existing model for this project and make a web application for the same using the best fitted model after the enhancement of the model implementation.
Name: Shruti Shrivastava
GitHub ID: theiturhs
Email ID: shrutishrivastava22ss@gmail.com
Idenitfy yourself: GSSOC'24

Closes: #583

Describe the add-ons or changes you've made 📃

Enhancing the model
- Data cleaning is performed which was necessary (for example: One feature 'Experience' had 56 negative values. Initially, this feature had a weak correlation with the target feature. However, after data cleaning, the correlation increased.)
- Type casting was performed. Nominal, Ordinal and Binary Data were converted to appropriate data type.
- Three Deep Learning algorithms are proposed - Feedforward Neural Network with K-Fold validation, TabNet with K-Fold validation and Wide and Deep Neural Network.
- TabNet model and encoders were saved to use it for prediction purpose.
Web Application using Flask
- A Flask based user application is made.
- It addresses some errors, including instances where the experience is greater than the age, or where the age is inconsistent with the education level.

Type of change ☑️

What sort of change have you made:

[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Code style update (formatting, local variables)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] This change requires a documentation update

How Has This Been Tested? ⚙️

Initially, I successfully ran the Flask application without any errors, verifying its smooth operation on the local server. For prediction purpose, I started with entering values which were provided in dataset itself. Next for addressing errors like age inconsistency with education level was also tested.

Checklist: ☑️

[x] My code follows the guidelines of this project.
[x] I have performed a self-review of my own code.
[x] I have commented my code, particularly wherever it was hard to understand.
[x] I have made corresponding changes to the documentation.
[x] My changes generate no new warnings.
[x] I have added things that prove my fix is effective or that my feature works.
[ ] Any dependent changes have been merged and published in downstream modules.

github-actions[bot] commented 1 month ago

Our team will soon review your PR. Thanks @theiturhs :)