https://github.com/bhaveshbhakta/loan-credit-prediction-using-ann

Loan Credit Prediction Using ANN
https://github.com/bhaveshbhakta/loan-credit-prediction-using-ann

artificial-neural-networks data-science data-visualization deep-learning fine-tuning loan loan-prediction loan-prediction-analysis machine-learning

Last synced: 6 days ago
JSON representation

Loan Credit Prediction Using ANN

• Host: GitHub
• URL: https://github.com/bhaveshbhakta/loan-credit-prediction-using-ann
• Owner: BhaveshBhakta
• Created: 2024-12-24T17:24:03.000Z (9 days ago)
• Default Branch: main
• Last Pushed: 2024-12-24T17:32:15.000Z (9 days ago)
• Last Synced: 2024-12-24T18:27:33.244Z (9 days ago)
• Topics: artificial-neural-networks, data-science, data-visualization, deep-learning, fine-tuning, loan, loan-prediction, loan-prediction-analysis, machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 476 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Loan-Credit-Prediction-Using-ANN

 

This repository provides Artificial Neural Network approach to predicting loan repayment status. The project involves comprehensive data exploration, visualization, preprocessing, model training, and evaluation, resulting in a high-accuracy prediction model to classify borrowers repayment behavior.

## Project Overview

This project aims to predict whether a borrower will fully repay their loan by leveraging various features like loan purpose, interest rate, FICO score, debt-to-income ratio, and more. By performing detailed data analysis and using advanced machine learning techniques, this project delivers a predictive model with significant accuracy, helping investors make informed decisions about loan repayments.

## Key Features

- **Comprehensive EDA:** Explored relationships and trends between features like loan purpose, interest rate, FICO score, and debt-to-income ratio.

- **Data Preprocessing:** Handled missing data, scaled numerical values, one-hot encoded categorical features, and addressed class imbalance using SMOTE.

- **Model Implementation:** Built, trained, and evaluated a neural network model for binary classification.

- **Performance Metrics:** Achieved an accuracy score of approximately 97%, demonstrating the model's effectiveness in predicting loan repayment status.

- **Actionable Insights:** Provided valuable predictions that can help investors assess the risk associated with lending.

## Purpose and Applications

This project is designed to:

- Provide accurate predictions regarding loan repayment behavior.

- Help investors make informed decisions by assessing the risk of lending to borrowers.

- Lay the foundation for exploring more complex algorithms or incorporating additional features in the future.

## Dataset

Dataset Link -([https://www.lendingclub.com](https://www.kaggle.com/datasets/itssuru/loan-data))

## Installation

Clone the repository:

```bash

git clone https://github.com/BhaveshBhakta/Loan-Credit-Prediction-Using-ANN.git

cd Loan-Credit-Prediction-Using-ANN

```

Run the notebook:

Open the `Loan-Credit-Prediction-Using-ANN.ipynb` file in Jupyter Notebook or any compatible IDE.

## Contributing

Contributions are welcome! Feel free to fork the repository, make improvements, and submit a pull request.