Log In Sign Up

Credit Card Fraud Detection Using Autoencoder Neural Network

by   Junyi Zou, et al.

Imbalanced data classification problem has always been a popular topic in the field of machine learning research. In order to balance the samples between majority and minority class. Oversampling algorithm is used to synthesize new minority class samples, but it could bring in noise. Pointing to the noise problems, this paper proposed a denoising autoencoder neural network (DAE) algorithm which can not only oversample minority class sample through misclassification cost, but it can denoise and classify the sampled dataset. Through experiments, compared with the denoising autoencoder neural network (DAE) with oversampling process and traditional fully connected neural networks, the results showed the proposed algorithm improves the classification accuracy of minority class of imbalanced datasets.


page 1

page 2

page 3

page 4


WOTBoost: Weighted Oversampling Technique in Boosting for imbalanced learning

Machine learning classifiers often stumble over imbalanced datasets wher...

Denoising without access to clean data using a partitioned autoencoder

Training a denoising autoencoder neural network requires access to truly...

An Efficient Convolutional Neural Network for Coronary Heart Disease Prediction

This study proposes an efficient neural network with convolutional layer...

Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

Some deep convolutional neural networks were proposed for time-series cl...

Neural Network Based Undersampling Techniques

Class imbalance problem is commonly faced while developing machine learn...

Image Denoising Using Convolutional Autoencoder

With the inexorable digitalisation of the modern world, every subset in ...

DEVDAN: Deep Evolving Denoising Autoencoder

The Denoising Autoencoder (DAE) enhances the flexibility of the data str...