To solve two main issues in credit card fraud detection - skewness of the data and cost-sensitivity
-
Updated
Jul 18, 2018 - Jupyter Notebook
To solve two main issues in credit card fraud detection - skewness of the data and cost-sensitivity
Credit card fraud recognition using two different approaches: autoencoders and random forests. This was the capston project that I have developed for the Machine Learning Engineer Nanodegree at Udacity.
Credit Card Fraud Detection using Neural Networks (Keras)
Credit Card Fraud Detection using KNN and K-means
This Repo contains Code and DataSet used with Results findout. I have used Logisitic Regression with Regulariztion, Plotted Graphs for Classfication applied Newton-Raphson Method .
Identify fraudulent credit card transactions.
Applied undersampling and oversampling using SMOTE.
Credit Card Fraud Detection model is developed to classify online transaction as either fradulent or genuine.
Includes Jupyter notebooks on some of my ML projects utilizing Sklearn, tensorflow, keras.These notebooks includes problems such as credit card fraud detection, digit recognization with clustering method, Stock market data analysis with KMeans clustering.Also, includes work on Natural Language Processing, Computer vision problems.
Predicting Credit Card Fraud Using Machine Learning Algorithms
Credit card fraud detection, gender classification from name etc.
Detect fraudulent transaction.
Detección de Fraude en tarjetas de crédito usando técnicas de data mining
Credit Card Fraud Detection using Decision tree and Support vector machine.
Credit Card Fraud Detection: Combination of both Unsupervised and Supervised Algorithm to detect Fraud in credit cards
Add a description, image, and links to the credit-card-fraud-detection topic page so that developers can more easily learn about it.
To associate your repository with the credit-card-fraud-detection topic, visit your repo's landing page and select "manage topics."