Credit Risk Default Score Prediction Project

Built with the tools and technologies:

---

Table of Contents

• Table of Contents
• Overview
• Roadmap
• Features
• Project Structure
  • Project Index
• Getting Started
  • Prerequisites
  • Installation
  • Usage
  • Testing
• Contributing
• License
• Acknowledgments

---

Overview

Credit Default Prediction — A machine learning project that predicts the likelihood of customer loan default to help financial institutions minimize credit risk. Built with Python, Scikit-learn, and Pandas, the model enhances data-driven lending and supports proactive risk mitigation.

Key Features:

Built predictive models using supervised learning algorithms ( - Linear Regression - KNN - Decision Tree - Random Forest - Stacking Regressor (using the above models as base estimators)).

Performed data cleaning, feature engineering, and model evaluation to ensure accuracy and reliability

Generated actionable insights to support data-driven lending decisions and default mitigation strategies

Tools & Technologies: Python, Scikit-learn, Pandas, NumPy, Matplotlib, Jupyter Notebook, Mlflow

Outcome: Improved prediction accuracy of default risk, enabling proactive financial decision-making and efficient credit portfolio management.

---

Roadmap

• Task 1: Perform Data ingestion (Ingesting data either from local-csv/database/API).
• Task 2: Perform Data transformation (train/test split, filling missing values, encoding).
• Task 3: Train the model (Models training).
• Task 4: Perform Model evaluation (Evaluate model; metrics = { "r2_score": r2, "rmse": rmse, "mae": mae } Also setup Mlflow for model & parameter tracking ).

---

Features

❯ 🗒️📌 Key Features Used

Feature Name	Description
income	Annual income of the applicant
loan_amount	Total amount of the requested loan
loan_term	Duration of the loan in months
interest_rate	Interest rate applied to the loan
debt_to_income_ratio	Ratio of total debt to annual income
employment_years	Years employed at current job
savings_balance	Current savings balance
age	Age of the applicant

---

Project Structure

└── /
    ├── .github
    │   └── workflows
    ├── api
    │   └── main.py
    ├── app.py
    ├── artifacts
    │   ├── data_ingestion
    │   ├── data_transformation
    │   ├── model_evaluation
    │   └── model_trainer
    ├── config
    │   └── config.yaml
    ├── Dockerfile
    ├── LICENSE
    ├── logs
    │   └── running_logs.log
    ├── main.py
    ├── notebook
    │   ├── data
    │   ├── EDA_DEFAULTPRED.ipynb
    │   ├── MODEL_TRAINER.ipynb
    │   └── trials.ipynb
    ├── params.yaml
    ├── README.md
    ├── requirements-streamlit.txt
    ├── requirements.txt
    ├── setup.py
    ├── src
    │   ├── defaultMlProj
    │   └── defaultMlProj.egg-info
    ├── template.py
    └── templates
        └── index.html

Project Index

/

__root__

⦿ __root__

File Name	Summary
app.py	Code>❯ Setup our frontend with streamlit
Dockerfile	Code>❯ Build image for model deployment
LICENSE	Code>❯ MIT License
main.py	Code>❯ Executes the data stages
params.yaml	Code>❯ Holds the model parameters
requirements-streamlit.txt	Code>❯ Necessary libraries for running steamlit frontend
requirements.txt	Code>❯ Libraries for running the project
setup.py	Code>❯ Project setup
template.py	Code>❯ Project template file

api

⦿ api

File Name	Summary
main.py	Code>❯ FASTAPI

config

⦿ config

File Name	Summary
config.yaml	Code>❯ Configuration file

notebook

⦿ notebook

File Name	Summary
EDA_DEFAULTPRED.ipynb	Code>❯ Notebook
MODEL_TRAINER.ipynb	Code>❯ Model trainer notebook
trials.ipynb	Code>❯ Trials notebook

templates

⦿ templates

File Name	Summary
index.html	Code>❯ HTML file

artifacts

⦿ artifacts

model_evaluation

⦿ artifacts.model_evaluation

File Name	Summary
metrics.json	Code>❯ Store the model metrics

model_trainer

⦿ artifacts.model_trainer

File Name	Summary
model.joblib	Code>❯ Store model artifacts

src

⦿ src

defaultMlProj.egg-info

⦿ src.defaultMlProj.egg-info

File Name	Summary
dependency_links.txt	Code>❯ Project pypi package links
PKG-INFO	Code>❯ Project pypi package
SOURCES.txt	Code>❯ REPLACE-ME
top_level.txt	Code>❯ REPLACE-ME

defaultMlProj

⦿ src.defaultMlProj

components

⦿ src.defaultMlProj.components

File Name	Summary
data_ingestion.py	Code>❯ Data ingestion file
data_transformation.py	Code>❯ Data transformation file
model_evaluation.py	Code>❯ Model evaluation file
model_trainer.py	Code>❯ Model trainer file

config

⦿ src.defaultMlProj.config

File Name	Summary
configuration.py	Code>❯ Config file

constants

⦿ src.defaultMlProj.constants

File Name	Summary
constant.py	Code>❯ Project constants file

entity

⦿ src.defaultMlProj.entity

File Name	Summary
config_entity.py	Code>❯ Project Config file

pipeline

⦿ src.defaultMlProj.pipeline

File Name	Summary
prediction.py	Code>❯ Model Prediction file
stage_data_ingestion.py	Code>❯ Data ingestion stage file
stage_data_transformation.py	Code>❯ Data transformation stage file
stage_model_evaluation.py	Code>❯ Model evaluation stage file
stage_model_trainer.py	Code>❯ Model tariner stage file

utils

⦿ src.defaultMlProj.utils

File Name	Summary
common.py	Code>❯ Common functions project file

---

Getting Started

Prerequisites

This project requires the following dependencies:

• Programming Language: Python
• Package Manager: Pip
• Container Runtime: Docker

Installation

Build from the source and intsall dependencies:

1. Clone the repository:

   ❯ git clone ../

2. Navigate to the project directory:

   ❯ cd 

3. Install the dependencies:

   Using docker:

   ❯ docker build -t / .

   Using pip:

   ❯ pip install -r requirements.txt

Usage

Run the project with:

Using docker:

docker run -it {image_name}

Using pip:

python {entrypoint}

Testing

uses the {test_framework} test framework. Run the test suite with:

Using pip:

pytest

---

Evaluation Metrics

Each model was evaluated using:

• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• R-squared (R²) Score

The best performing model selected based on these metrics.

• ✅ Stacking Regressor

---

Contributing

• 💬 Join the Discussions: Share your insights, provide feedback, or ask questions.
• 🐛 Report Issues: Submit bugs found or log feature requests for the `` project.
• 💡 Submit Pull Requests: Review open PRs, and submit your own PRs.

Contributing Guidelines

1. Fork the Repository: Start by forking the project repository to your LOCAL account.
2. Clone Locally: Clone the forked repository to your local machine using a git client.

   git clone .

3. Create a New Branch: Always work on a new branch, giving it a descriptive name.

   git checkout -b new-feature-x

4. Make Your Changes: Develop and test your changes locally.
5. Commit Your Changes: Commit with a clear message describing your updates.

   git commit -m 'Implemented new feature x.'

6. Push to LOCAL: Push the changes to your forked repository.

   git push origin new-feature-x

7. Submit a Pull Request: Create a PR against the original project repository. Clearly describe the changes and their motivations.
8. Review: Once your PR is reviewed and approved, it will be merged into the main branch. Congratulations on your contribution!

Contributor Graph

---

License

is protected under the LICENSE License. For more details, refer to the LICENSE file.

---

Acknowledgments

• Credit contributors, inspiration, references, etc.

---