Skip to content

This repository contains my take at software, verifying whether a bank statement is authentic. It uses various techniques including simple numerical comparisons, machine learning, and AI vision model out-sourcing.

Notifications You must be signed in to change notification settings

rokasauras/FinCheck

Repository files navigation

FinCheck

This repository contains software designed to verify the authenticity of bank statements. It integrates numerical analysis, machine learning, and outsourced AI vision analysis.

Getting Started

1. Clone Repository

git clone https://github.com/rokasauras/FinCheck

2. Install Required Libraries

Ensure you have Python installed. Navigate to the project folder and install the required libraries:

pip install -r requirements.txt

Required Libraries Include:

  • openai
  • pdf2image
  • PyPDF2
  • python-dotenv
  • streamlit
  • matplotlib
  • pandas
  • numpy
  • scikit-learn
  • sqlite3

You may also require the installation of poppler for PDF image conversion:

3. Set Up Environment Variables

Create a OpenAI.env file in your project directory containing:

OPENAI_API_KEY="your_openai_api_key_here"

4. Configure File Paths

Ensure all file paths specified in:

  • main.py
  • SQLPreper.py
  • MachineLearning.py

point correctly to your local directories. Adjust paths explicitly marked in these scripts.

5. Run the Application

Open the project folder in VS Code, open a terminal, and execute:

python main.py

This will initiate the pipeline for bank statement verification.

Additional Usage

To utilise the web interface locally, run:

streamlit run app.py

Then open your browser to the URL displayed in the terminal.

Troubleshooting

  • Ensure the paths to files and the database are correctly set.
  • Verify the OpenAI API key is valid and correctly loaded.

License

This project is for educational and demonstrative purposes only.

About

This repository contains my take at software, verifying whether a bank statement is authentic. It uses various techniques including simple numerical comparisons, machine learning, and AI vision model out-sourcing.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages