Skip to content

Fraud Detection System, Using XGBoost and Flask at the Backend with React at the Frontend

Notifications You must be signed in to change notification settings

Bella-ciaoo/BerTrugS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 

Repository files navigation

BeTrugS 🕵🏻‍♀️

BeTrugs is an application which is used for the detection and forecatsing of fradulent transactions ina financial system. The user will input the transaction id and the percentage of predicted fraud will be displayed to the user along with the details of the transaction.


Framework 🧑‍💻 :

Frontend:

  • React JS

Machine Learning(libraries):

  • XGBoost

  • Sklearn

  • Numpy

  • Pandas

  • Seaborn

  • Matplotlib

Backend:

  • Flask

Deployment:

  • Azure

How it works📃:

At first a manual insight is taken on the which attributes will be taken into consideration i.e the data from the dataset is cleaned/classified. The data is proccessed and a model is trained based on the data such that the percentage of the chance of a fradulent transaction is returned.

Suggested Steps to prevent fraudulent transactions :

  • Regular Security Upgrades in financial systems

  • Block Suspicious IP addresses

  • Notify User when a transaction seems sceptical

  • Add biometric confirmation (eg-fingerprint) before transfer

  • Use blockchain to avoid anonymity

Colab Notebook link

https://colab.research.google.com/drive/14S8Wk0wYyZDTIakCdSZ0Bjj8qyv6rPkQ?usp=sharing

Rough Notebook

https://colab.research.google.com/drive/1nto_-SrffLq06DvogqvsBUL6EDF33AeA?usp=sharing

Presentation

https://docs.google.com/presentation/d/16mXcSJu_MH01vw8Z5rDBK-2ORdENfaOrRBvfnaisJ9o/edit?usp=sharing

Contributors


With ❤️  by Bella Ciao