DS Notebooks

IEEE Fraud Detection with XGBoost and CatBoost

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

IEEE-CIS Fraud Detection Kaggle Competition notebooks

Detecting fraudulent credit card transactions using machine learning.

🛡️ SecureCard-AI: A high-performance credit card fraud detection system implemented in a Jupyter Notebook, achieving 99.97% accuracy.

Fraud Detection in E-Commerce (SQL)

Fraud Detection using XGBoost on a 6M+ transaction dataset with 97% ROC-AUC. (Business insights also included.)

Repository to share the development of three machine learning tasks as part of the Cognorise Internship Data Science program

This is a notebook for fraud detection for a kaggle challenge.

This repository contains some of my machine learning notebooks I created on Kaggle

ML portfolio project: fraud detection with reproducible notebooks, model card, datasheet, and tuned decision threshold.

ML-powered fraud detection for UPI transactions | 87% F1-Score | XGBoost + Flask | Real-time predictions | Interactive notebooks

This repository contains a Jupyter Notebook for Credit Card Fraud Detection Model and a csv dataset on which it is being trained

This repo has a notebook that I worked on for making a fraud detection model. The dataset was Highly imbalanced, so i used random undersampling to balance the data.

In this notebook we take a look at a relevant project that is frequently encountered by insurers: Fraud Detection. For this purpose we use a car data set from a public source and will show the necessary steps to establish an automated fraud detection.

This project implements a machine learning-based fraud detection system for financial transactions. It includes a Jupyter notebook for exploratory data analysis (EDA) and model training, a Streamlit web application for interactive fraud predictions

My capstone project for Fullstack Academy's Data Analysis program. Analyzes ~100MB credit card transaction data for fraud patterns using Jupyter Notebook (Python preprocessing, MySQL batch insertion), SQL scripts, Tableau dashboard, and Excel files.

A notebook about credit card fraud detection treated as anomaly detection via multivariative normal distribution. The dataset is highly imbalanced (0.17 % of positive class labels). Dataset source: https://www.kaggle.com/mlg-ulb/creditcardfraud

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