Bankruptcy Prediction Project

Introduction

Welcome to the Bankruptcy Prediction Project! This repository contains code and resources for predicting bankruptcy in UK retail companies based on financial ratios data from 2017 to 2021. The project aims to help retail businesses become more aware of their financial situation and identify key financial ratios that are crucial in avoiding bankruptcy risks.

Installation

1. Clone the repository:

   git clone https://github.com/abdullah9041/Bankruptcy-Prediction.git
   cd your-repo-name

2. Set up a virtual environment (optional but recommended):

   python -m venv venv
   source venv/bin/activate

3. Install the required dependencies:

   pip install -r requirements.txt

Usage

1. Prepare your dataset files (inactive and active companies) in Excel format and update paths in config.py.

2. Customize config.py with dataset paths and configuration.

3. Run the main script:

   python main.py

4. Explore output results and visualizations. The project uses ML algorithms like Logistic Regression, k-NN, Random Forest, Neural Networks, Linear SVM.

Features

• Data cleaning and preprocessing.
• Exploratory data analysis (EDA) with visualizations.
• Train-test split and data normalization.
• Implementation of ML algorithms.
• Hyperparameter tuning and model evaluation.

Contributing

Contributions welcome! Follow these steps to contribute:

1. Fork the repository.
2. Create a new branch for your work.
3. Make changes, write tests if needed.
4. Test thoroughly.
5. Submit a pull request explaining your changes.

License

This project is licensed under the MIT License.