Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 1
Abstract
Frauds have no constant patterns. They always change their behavior; so, we need to use an unsupervised learning. Fraudsters learn about new technology that allows them to execute frauds through online transactions. Fraudsters assume the regular behavior of consumers, and fraud patterns change fast. So, fraud detection systems need to detect online transactions by using unsupervised learning, because some fraudsters commit frauds once through online mediums and then switch to other techniques. This paper aims to 1) focus on fraud cases that cannot be detected based on previous history or supervised learning, 2) create a model of deep Auto-encoder and restricted Boltzmann machine (RBM) that can reconstruct normal transactions to find anomalies from normal patterns. The proposed deep learning based on auto-encoder (AE) is an unsupervised learning algorithm that applies backpropagation by setting the inputs equal to the outputs. The RBM has two layers, the input layer (visible) and hidden layer. In this research, we use the Tensorflow library from Google to implement AE, RBM, and H2O by using deep learning. The results show the mean squared error, root mean squared error, and area under curve.
Authors and Affiliations
Apapan Pumsirirat, Liu Yan
Keywords
Related Articles
- EP ID EP261407
- DOI 10.14569/IJACSA.2018.090103
- Views 82
- Downloads 0
Hybrid Technique for Java Code Complexity Analysis
Software complexity can be defined as the degree of difficulty in analysis, testing, design and implementation of software. Typically, reducing model complexity has a significant impact on maintenance activities. A lot o...
An Approach of nMPRA Architecture using Hardware Implemented Support for Event Prioritization and Treating
One of the fundamental requirements of real time operating systems is the determinism of executing critical tasks and treating multiple periodic or aperiodic events. The present paper presents the hardware support of the...
Optimizing the Locations of Intermediate Rechlorination Stations in a Drinking Water Distribution Network
The preservation of the water quality in the distribution network requires maintaining permanently minimum residual chlorine at any point of the network. This is possible only if we plan chlore’s injections in various po...
An Enhanced Breast Cancer Diagnosis Scheme based on Two-Step-SVM Technique
This paper proposes an automatic diagnostic method for breast tumour disease using hybrid Support Vector Machine (SVM) and the Two-Step Clustering Technique. The hybrid technique is aimed at improving the diagnostic accu...
The Designing of Adaptive Self-Assessment Activities in Second Language Learning using Massive Open Online Courses (MOOCs)
Massive Open Online Courses (MOOCs) provides an effective learning platform with various high-quality educational materials accessible to learners from all over the world. In this paper, the types of learner characterist...