https://github.com/rahulb813/overdraft-conjecture

An SVM based prediction model to predict bank loan status
https://github.com/rahulb813/overdraft-conjecture

Last synced: 10 days ago
JSON representation

An SVM based prediction model to predict bank loan status

• Host: GitHub
• URL: https://github.com/rahulb813/overdraft-conjecture
• Owner: rahulb813
• License: gpl-3.0
• Created: 2023-11-18T19:44:15.000Z (almost 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-18T20:01:34.000Z (almost 1 year ago)
• Last Synced: 2023-11-19T20:37:47.538Z (12 months ago)
• Language: Jupyter Notebook
• Size: 150 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# OverDraft Conjecture

## Introduction

-   An SVM based ML model that's trained with a dataset with 600+ values.

-   Predicts yes/no prediction status for bank loans.

## Intuition

The use of SVM is done because the final output predicted by this model

is supposed to be a binary value which results that the loan confirmation is real or fake.

## Technologies Used

-   Python

-   sklearn

-   numpy

-   seaborn

## Dataset

A single [`dataset.csv`](https://www.kaggle.com/datasets/ninzaami/loan-predication/) dataset obtained from [Kaggle](https://wwww.kaggle.com) is used

## Testing

The model is trained with 80% and tested with 20% of the [`train.csv`](https://www.kaggle.com/c/fake-news/data) dataset and the accuracy of the model was 79% and 83% respectively.

## Deployment

A live version of the [`main.ipynb`](https://github.com/rahulb813/veracious-prophecy/blob/main/main.ipynb) is uploaded at [Google Drive](https://drive.google.com/drive/folders/1Dc3zftve6CMrDUYRBGGlmaVQ3w-pfdku?usp=sharing).