A data science project to predict whether a transaction is a fraud or not.

💳 Creates a new gym environment for credit-card anomaly detection using Deep Q-Networks (DQN) and leverages Open AI's Gym toolkit to allocate appropriate awards to the RL agent.

System to tell apart the transaction was from the real user who owns the credit card or the transaction was from the stolen credit card.

Project for the Big Data Computing course at the University of "La Sapienza" in Master in Computer Science A.A. 2021/2022

This notebook tries to make fraud/not fraud predictions on a transactions dataset with highly imbalanced data.

This is my final project for my internship at EISystems Technologies. I have used two ML algorithms and tried my hands-on. Also, the final report is included.

Detection of fraudulent transactions from IEEE Kaggle Dataset

This project aims to detect fraudulent transactions in the Ethereum blockchain using machine learning algorithms. Fraud detection is crucial for maintaining the integrity and security of the blockchain, and can help prevent financial losses due to fraudulent activity.

Focused on advancing credit card fraud detection, this project employs machine learning algorithms, including neural networks and decision trees, to enhance fraud prevention in the banking sector. It serves as the final project for a Data Science course at the University of Ottawa in 2023.

This project uses predictive modeling techniques to identify fraudulent Credit Card transactions on data obtained from European credit card holders made in September 2013.

Catering to Blocker Fraud Company's expansion in Brazil, this data science and machine learning project focuses on detecting fraudulent financial transactions. Leveraging advanced analytics, it delivers insights into transaction legitimacy, aiding revenue generation and minimizing losses

In this repo I have used SQL to analyze historical credit card transactions and consumption patterns in order to identify possible fraudulent transactions.

Building an online payment fraud detection system using machine learning algorithms. It utilizes three primary classification algorithms - Logistic Regression, Decision Tree, and Random Forest - to analyze and classify transactions as either legitimate or fraudulent.

💳 Creates a new gym environment for credit-card anomaly detection using Deep Q-Networks (DQN) and leverages Open AI's Gym toolkit to allocate appropriate awards to the RL agent.

🔍 Predict fraudulent transactions with a pre-trained Random Forest Classifier model via Streamlit app.

🛒 Provide a robust model that assists in flagging suspicious transactions, ultimately helping businesses improve security and reduce financial losses.

Credit Card Transactions Fraud Detection using Deep Learning.

Fraud transaction detection using Machine Learning algorithms on highly imbalanced dataset

Code to detect credit card fraud detecton

Fraud Detection Data