🚨 Fraud Detection with Deep Neural Networks (PoC) 🤖 A hands-on personal project to predict fraudulent financial transactions using deep learning. Covers the full pipeline: from exploratory data analysis (EDA) and preprocessing to model training and evaluation. An experimental approach to tackling real-world financial fraud. 📊🔍

Credit Fraud Detection for the course project for the master's degree in Software and Systems Engineering.

Developed and evaluated machine learning and deep learning models for detecting financial fraud.

ML-FinFraud-Detector is a machine learning project for detecting financial transaction fraud. Utilizing XGBoost, precision-recall, and ROC curves, it provides accurate fraud detection. Explore feature importance, evaluate model performance, and enhance financial security with this comprehensive fraud detection solution.

The Wirecard scandal is considered one of the largest financial scandals of the decade, which caused losses of several billion euros. This analysis examines the digit structure of Wirecard's financial figures in the period from 2005 to 2019 by analyzing the conformity with the expected frequency distributions according to Benford's law. The results show that company-specific accounting fraud cannot be detected by Benford analysis of the first, second, and first-two significant digits alone.

Enterprise-grade fraud & AML detection with ML and deep learning (XGBoost, LightGBM, Autoencoder, LSTM, Transformer). Real-time API, explainability (SHAP), BI export, Streamlit dashboard. PaySim-compatible.

🛡️ Welcome to our Credit Card Fraud Detection project! 💳 Harnessing the formidable prowess machine learning, we're steadfast in our mission to fortify your financial stronghold against deceitful adversaries. Join our crusade for financial resilience,Ensuring every transaction is securely monitored! 🔐💯

A sophisticated platform for anomaly detection in transaction data using autoencoders. Integrates SQL database connectivity, hyperparameter optimization, entropy analysis, and comprehensive visualizations. Tailored for financial fraud detection and industrial data analytics. (280 characters)

Source code of the paper entitled "Spiking Alternatives for the Leaky Integrate-and-Fire Neuron: Applications in Cybersecurity and Financial Threats", and presented at IbPRIA 2025, the 12th Iberian Conference on Pattern Recognition and Image Analysis.

Detect financial fraud with ML-powered predictions via an interactive Streamlit app.

ML model developed using European credit card transaction data to identify suspicious activities.

Unsupervised anomaly detection for credit card fraud using Gaussian Mixture Models (GMMs). Models legitimate behavior via probability density estimation and flags low-likelihood transactions as potential frauds.

Analysis and detection of potentially fraudulent credit card transactions in USA based on transaction duplication, transaction frequency, transaction duration, geolocation, and movement speed transaction. This repository includes informative visualizations, handling of imbalanced data challenges, fraud detection model, and performance evaluation.

An informative website built with HTML, CSS, and JavaScript to raise public awareness about financial fraud and how to protect against scams through education and prevention tips.

Application built for example financial company that predicts if a transaction is fraudulent. Model trained on sample data from kaggle

Explainable AI (XAI) based system for detecting financial fraud using machine learning, with model interpretability, analysis, and research-backed implementation.