Financial Risk Assessment Demo

This project is a demonstration of a Financial Risk Assessment application that predicts risk tolerance based on user-provided financial data. It combines machine learning models (Logistic Regression and LightGBM), FastAPI for the backend, and Streamlit for the frontend to create an interactive web application.

Overview
Project Structure
Getting Started
Usage
Demo
Dependencies

Overview

The goal of this project is to showcase the integration of machine learning models into a web-based financial risk assessment tool. It includes:

Data generation (mock data for demonstration purposes).
Risk assessment models (Logistic Regression and LightGBM).
A FastAPI backend for handling user requests.
A Streamlit frontend for user interaction.

Project Structure

The project is organized as follows:

financial_demo/
│
├── data/
│   └── financial_data.csv
│
├── scripts/
│   ├── generate_data.py
│   ├── risk_assessment.py
│   └── ...
│
├── models/
│   ├── risk_assessment_model.joblib
│   ├── risk_assessment_model_xgb.joblib
│   └── ...
│
├── app.py
├── streamlit_app.py
├── requirements.txt
└── README.md

data/: Contains the mock financial dataset.
scripts/: Includes Python scripts for data generation and model training.
models/: Stores trained machine learning models.
app.py: The FastAPI backend for risk assessment.
streamlit_app.py: The Streamlit frontend for user interaction.
requirements.txt: Lists project dependencies.

Getting Started

To run the project locally, follow these steps:

Clone this repository to your local machine:

git clone https://github.com/fshnkarimi/Financial-Risk-Assessment-using-LightGBM.git
cd Financial-Risk-Assessment-using-LightGBM

Set up a virtual environment (optional but recommended):

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Install project dependencies:
```
pip install -r requirements.txt
```
Generate mock financial data:
```
python scripts/generate_data.py
```
Train the risk assessment model (Logistic Regression or LightGBM):
```
python scripts/risk_assessment.py
```
Start the FastAPI backend:
```
uvicorn app:app
```
In a separate terminal, run the Streamlit app:
```
streamlit run streamlit_app.py
```
Access the Streamlit app in your web browser (usually at http://localhost:8501).

Usage

Open the Streamlit app in your web browser.
Enter your financial data, including income and expenses.
Click the "Assess Risk" button to receive a risk assessment result.

Demo

Dependencies

scikit-learn
fastapi
pydantic
lightgbm
streamlit
joblib
requests

For a complete list of dependencies, see requirements.txt.

fshnkarimi/Financial-Risk-Assessment-using-LightGBM