Table of Contents
The goal of our concept is to create a scalable solution that will benefit the e-commerce ecosystem by reducing identity and payment fraud through analysis of transaction and behavioural data. Other third-party clients can effortlessly integrate our service with the use of an API key. It will also assist them in conserving resources by using our model as a service.
Our idea consists of 3 major components, namely the Android App, the Web App, and the Machine Learning Model.
Android Application: To determine whether a transaction is fraudulent before the order is confirmed, we will create a minimally viable e-commerce software that will be connected to a machine learning model via a backend API.
Web App : To demonstrate how easily the backend API can be incorporated into any platform, we'll develop a functionality similar to the Android application.
Fraud Detection Model: We have used random forest on our dataset to determine whether a transaction is fraudulent or not by using information from the e-commerce platform, such as the IP address, billing address, purchase amount, etc. The model will be deployed on a scalable microservice architecture.
Later on, we will focus more on our system's scalability and security, as well as adding new features to extend our current implementation for third-party clients to add their own restrictions and logic.
We will also work to improve the detection model by utilising an elaborate dataset with more features, such as tracking of user actions performed prior to purchasing a product.
We will also include a feedback mechanism to help the model learn from its mistakes and improve.
The business model will also be launched as a ** pay-per-use** model, which will benefit both small and large businesses.
Mobile Applicaton:
- Flutter
- Firebase
- Backed Model
You can test HackOn Shop in your own development environment. This section shows you how:
You'll need to set up the IDE and mobile device emulator, or any mobile testing device on your local system.
Flutter Environment: You'll need to have the following installed:
Ensure you are testing the app using Flutter version 2.10.5 and above.
For checking flutter version:
- Run flutter --version in terminal
If your version is not upto date, follow these steps to upgrade:
- flutter channel stable to switch to the channel having stable version of flutter updates
- flutter upgrade to get the latest flutter version
-
Clone this repository after forking using git clone https://github.com/pnkr01/Fraud_Detection
-
cd into
quick_order
-
Check for flutter setup and connected devices using
flutter doctor
-
Get all the dependencies using
flutter pub get
-
Run the app using
flutter run
For help getting started with Flutter, view our online documentation, which offers tutorials, samples, guidance on mobile development, and a full API reference.
This project structure:
QUICCK_ORDER/lib/
├── src/
├── global/
├── components
├── constants
├── ...
└──.....
├── model
├── cart
├── product
└── category
├──screens
├── account
├── account.dart
├── cart
├── components
├── ...
├── ...
├── ...
└── cart_screen.dart
├── details
├── components
├── ...
├── ...
├── ...
└── details.dart
├── home
├── components
├── ...
├── ...
└── ...
└── home_screen.dart
├── splash
├── components
├── ...
├── ...
├── ...
└── splash.dart
├── services
├── api
└── ip_address.dart
├── auth
├──components
├── new_user
├── old_user
└── profile
└── sigin.dart
├──app_theme.dart
└──app.dart
└── main.dart # Heart of this App.
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Distributed under the MIT License. See LICENSE
for more information.
Team Name - Seh_Lenge_Thoda
Pawan Kumar
Saheb Giri
Gyanaranjan
Rahul Kumar
Project Link: Link
Made with ♥ by Team Seh_Lenge_Thoda in HackOn with Amazon .