Credit card fraud detection using RUS and MRN algorithms

Charleonnan, Anusorn

doi:10.1109/miticon.2016.8025244

Cited by 19 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two major methods of adjusting the imbalance in datasets, undersampling and oversampling. In his research, he also uses the MRN algorithm for the classification problem of credit card fraud [6].…”

Section: Related Workmentioning

confidence: 99%

Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine

Pumsirirat¹,

Liu²

2018

ijacsa

193

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine

Pumsirirat¹,

Liu²

2018

ijacsa

193

View full text Add to dashboard Cite

show abstract

“…Benmakrouha et al to elucidate consumer behavior profile, transaction amount and time of shopping is thought-out as inputs and output is suspicious but the model have yet to be developed and tested with real data. Data mining techniques for fraud detection in credit card management based on customer behaviors can improve performance concerning accuracy and sensitivity [24]. 2315 A multifactor authentication system was proposed to which knowledge factor is a 4-digit pin, possession factor is NFC-enabled Smartphone and inherence factor is the face of the user [25].…”

Section: Research Methods 21 Related Workmentioning

confidence: 99%

An empiric path towards fraud detection and protection for NFC-enabled mobile payment system

Vishwakarma¹,

Tripathy

Vemuru³

2019

TELKOMNIKA

View full text Add to dashboard Cite

The synthesis of NFC technology accompanying mobile payment is a state-of-the-art resolution for payment users. In view of rapid development in electronic payment system there is rise in fraudulent activity in banking transactions associated with credit cards and card-not-present transaction. M-Commerce aid the consumers and helps to bestow real-time information in payment system. Due to the familiarization of m-commerce there is cogent increase in the number of fraudulent activities, emerging in billions of dollar loss every year worldwide. To absolute the security breaches, payment transactions could be confined by considering various parameters like user and device authentication, consumer behavior pattern, geolocation and velocity. In this paper we formally assay NFC-enabled mobile payment fraud detection ecosystem using score-based evaluation method. The fraud detection ecosystem will provide a solution based on transaction risk-modeling, scoring transaction, business rule-based, and cross-field referencing. The score-based evaluation method will analyze the transaction and reckon every transaction for fraud risk and take pertinent decision.

show abstract

“…Conclude that KNN algorithm extremely well in CCFD (Credit Card Fraud Detection). A similar research domain was presented by Anusorn Charleonnan [2] they proposed a new algorithm "RUSMRN algorithm" based on three classifiers which are RUS, MRN and Naïve Bayes algorithms. The author gives a basic description about these three algorithms and proposed an algorithm step by step.…”

Section: IImentioning

confidence: 98%

Credit Card Fraud Detection for Online Banking Transactions

Naik¹

2018

IJRASET

View full text Add to dashboard Cite

Credit card fraud detection using RUS and MRN algorithms

Cited by 19 publications

References 6 publications

Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine

Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine

An empiric path towards fraud detection and protection for NFC-enabled mobile payment system

Credit Card Fraud Detection for Online Banking Transactions

Contact Info

Product

Resources

About