Semi-Supervised Classification on Credit Card Fraud Detection using AutoEncoders

The use of credit cards for online purchases has increased dramatically and led to an explosion in card fraud. Credit companies need be able identify fraudulent transactions so that customers are not charged items they do buy. In this study, we will semi-supervised learning combine it with AutoEncoders transactions. paper, implement the T-SNE visualize fraud non-fraud transactions, then improve visualization using autoencoders. Classification report proved is possible achieve very acceptable precision classification detect