Detecting fraudulent credit card transactions using deep learning.
Final Paper can be found at: /paper/FinalPaper.pdf
The credit card fraud dataset is not included in this repository because of size limitations, but can be downloaded from https://www.kaggle.com/mlg-ulb/creditcardfraud/data After downloading, place the creditcard.csv file in the same directory as the learn.py file for running.
To run the learning:
On Both Platforms: Ensure that python and the pandas/tensorflow packages are installed.
On Linux:
- Change directory to src_linux
- Change the learn.py file execution permission to true
- Run with ./learn.py
On Windows:
- Change directory to src_win
- Open the Visual Studio solution file in VS 2017
- Rrun from the IDE.
The /results/ folder contains the data used in all charts in the paper