Cdc Fraud Detection Demo

Abstract

1. Introduction

Realtime Credit Card fraud detection, using CDC (Change Data Capture) data source and TensorFlow model from a Kaggle competition.

Prerequisite: At least 6-7GB needs to be provided to your Docker daemon!

2. Objective

Realtime Credit Card fraud detection, using CDC (Change Data Capture) data source and TensorFlow model from a Kaggle competition.

This project demonstrates how Java can be applied to a real-world AI & Machine Learning problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• JDK 11 or later
• Maven / Gradle
• IntelliJ IDEA, Eclipse or Android Studio
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/tzolov/cdc-fraud-detection-demo.git
cd cdc-fraud-detection-demo

1. Checkout the https://github.com/tzolov/cdc-fraud-detection-demo project and change the local directory to docker:
2. Download the Spring Cloud Data Flow Server docker-compose, docker-compose-prometheus and docker-compose-dood installation files:
3. Make sure that all the docker-compose.yml, docker-compose-prometheus.yml, docker-compose-dood.yml and the docker-compose.fraud.yml files are present in the local directory and then start run:
4. It may take two, three minutes for all containers and services to start. Once ready you should see the following running containers:
5. Open the SCDF Web dashboard at http://localhost:9393/dashboard/#/streams/definitions and navigate to the Stream definitions.
6. Press ‘Create New Stream’ button and add the following streams:
7. Press Create Stream button.
8. Deploy both (fraud-detection and fraud-log) stream. Wait until all apps are deployed

git clone git@github.com:tzolov/cdc-fraud-detection-demo.git
cd cdc-fraud-detection-demo/docker

wget https://raw.githubusercontent.com/spring-cloud/spring-cloud-dataflow/main/src/docker-compose/docker-compose.yml

wget https://raw.githubusercontent.com/spring-cloud/spring-cloud-dataflow/main/src/docker-compose/docker-compose-dood.yml

wget https://raw.githubusercontent.com/spring-cloud/spring-cloud-dataflow/main/src/docker-compose/docker-compose-prometheus.yml

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by tzolov and published on GitHub under the Apache License 2.0. Please follow the license terms and credit the original author when you use or modify this code.