Fraud Detection System
A sophisticated real-time transaction monitoring application using machine learning to detect fraudulent activities.
Problem
Smaller financial institutions needed a fraud detection tool they could run without cloud infrastructure or specialist ML teams — existing solutions were expensive, online-only, and opaque in their decision logic.
Solution
Built a self-contained JavaFX desktop app that loads transaction datasets, trains a Weka ML classifier in-process, and surfaces real-time fraud alerts stored in an embedded H2 database — fully offline and auditable.
Achievements
- Real-time transaction classification with Weka
- Embedded H2 database for tamper-evident audit logs
- Fully offline — no cloud dependencies
- Transparent decision logic via Weka model inspection
The Fraud Detection System is a desktop application that empowers smaller institutions to flag suspicious transactions in real time using machine learning — without requiring cloud infrastructure, an internet connection, or specialist ML expertise.
- User loads a CSV of transactions into the application
- Weka trains a classifier on labelled training data
- Each new transaction is scored in real time and flagged if above the fraud threshold
- All results are persisted in the H2 database for audit review
- CSV transaction ingestion with automatic feature extraction
- In-process ML classification using Weka algorithms
- Real-time fraud alert dashboard with JavaFX UI
- H2 embedded database for persistent, auditable transaction logs
- Fully offline — no network required for inference
- Maven build system for reproducible packaging