Team ID | PNT2022TMID18010 |
---|---|
Domain | Applied Data Science |
Project Name | SMART LENDER - Applicant Credibility Prediction For Loan Approval |
Team Member | Name | Register Number |
---|---|---|
Team Leader | Pranava Kailash S P | 713319CS107 |
Team Member-1 | Dharshana R | 713319EC024 |
Team Member-2 | Monica V | 713319CS079 |
Team Member-3 | Keerthana S | 713319CS063 |
The credit system managed by banks is one of the most important variables affecting our country's economic and financial situation. Bank credit risk appraisal is a recognised technique in banks worldwide. "As we all know, credit risk evaluation is critical, and a number of methodologies are utilised to calculate risk level." Furthermore, credit risk is one of the financial community's primary functions.
One of the most challenging challenges for any bank is predicting loan defaulters. However, by projecting loan defaulters, banks may surely limit their loss by lowering their non-profit assets, so that authorised loans can be recovered without any loss, and it can play a contributing aspect of the bank statement. This emphasises the need of researching loan approval prediction. Machine Learning algorithms are extremely important and useful in predicting this sort of data.
Web UI
- Hyper Text Markup Language
- Cascading Style Sheets
- JavaScript
Integration
- Python Flask
Model Building
- Pandas
- Numpy
- Scikit learn
Performance Testing
- Gatling
Load Testing
- Locust
Please install the required dependence on your Local Machine before running the ibm_app.py
The required dependences are as follows:
pip install flask
pip install numpy
pip install pickle
pip install requests
Also make sure you have the scale.pkl and templates files, before your run the ibm_app.py
- Pranava Kailash - Model Building, Integration, Testing
- Dharshana - Web UI, Integration, Testing
- Monica, Keerthana - Literature Survey, Documentation