Neural data mining for credit card fraud detection

Brause, Rüdiger; Langsdorf, Timm Sebastian; Hepp, Martin

doi:10.1109/tai.1999.809773

Cited by 210 publications

(122 citation statements)

References 5 publications

Supporting

Mentioning

120

Contrasting

Unclassified

Order By: Relevance

“…Many credit card fraud detection studies report a fraud ratio of less than 0.5% (Brause et al, 1999;Shen et al, 2007;Sánchez et al, 2009;Bhattacharyya et al, 2011;Duman and Elikucuk, 2013;Bahnsen et al, 2013Bahnsen et al, , 2014Dal Pozzolo et al, 2014).…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…More studies focus on supervised techniques using evidence of past fraudulent transactions to infer the suspiciousness of future transactions. The most prevalent technique for supervised credit card fraud detection is artificial neural networks (ANN's) (Ghosh and Reilly, 1994;Aleskerov et al, 1997;Dorronsoro et al, 1997;Brause et al, 1999;Maes et al, 2002;Syeda et al, 2002;Shen et al, 2007). While ANN's generally achieve a high performance, they are black box models which lack interpretability.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

See 1 more Smart Citation

APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions

Vlasselaer

Bravo

Caelen³

et al. 2015

Decision Support Systems

278

142

View full text Add to dashboard Cite

In the last decade, the ease of online payment has opened up many new opportunities for e-commerce, lowering the geographical boundaries for retail. While e-commerce is still gaining popularity, it is also the playground of fraudsters who try to misuse the transparency of online purchases and the transfer of credit card records. This paper proposes APATE, a novel approach to detect fraudulent credit card transactions conducted in online stores. Our approach combines (1) intrinsic features derived from the characteristics of incoming transactions and the customer spending history using the fundamentals of RFM (Recency -Frequency -Monetary); and (2) network-based features by exploiting the network of credit card holders and merchants and deriving a time-dependent suspiciousness score for each network object. Our results show that both intrinsic and network-based features are two strongly intertwined sides of the same picture. The combination of these two types of features leads to the best performing models which reach AUC-scores higher than 0.98.

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Accepted Manuscriptmentioning

confidence: 99%

APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions

Vlasselaer

Bravo

Caelen³

et al. 2015

Decision Support Systems

278

142

View full text Add to dashboard Cite

show abstract

“…A group researcher from different study have proposed credit card fraud detection with a neural network [4][5][6][7].…”

Section: Single Classification Methodsmentioning

confidence: 99%

Overdue Prediction of Bank Loans Based on Deep Neural Network

Li¹,

Sun²,

Li³

2017

International Symposium on Computer Science and Artificial Intelligence(ISCSAI)

View full text Add to dashboard Cite

With the development of information technology, the application of big data in financial aspects becomes more and more deepening. However, in the aspect of bank loans, the accuracy of traditional user loan risk prediction models, such as KNN, Bayesian, are not benefit from the data growth.This paper proposes to use DNN algorithm to forecast the risk of user loan based on the difficulties of current overdue prediction and the excellent learning ability of DNN. This article uses user basic information, bank records, user browsing behavior, credit card billing records, and loan time information to evaluate whether users are delinquent. Firstly, this paper record bank records according to the transaction type, respectively, to generate income and spending data. Secondly, to sum the user browsing behavior also, and to record the average of credit card bill. In addition, in order to reduce the effect of eigenvalue size on the result, all characteristics are standardized. Finally, users who lack user information are discarded and the above fields are spliced. The spliced fields are the basic input for DNN. From the experimental results, DNN algorithm increase over 6% prediction than kNN, Bayes algorithm.

show abstract

“…Artificial Neural Networks (ANN) being one of the mostly used machine learning techniques, is one of the most suitable mechanisms for identifying anomalies. This area has witnesses a huge contribution towards anomaly detection [7][8][9][10][11][12][13]21]. Several ensemble methods that work well in such applications include random forests [14], SVM [15] genetic algorithms [16] and hidden Markov models [17].…”

Section: Related Workmentioning

confidence: 99%

Enhanced Anomaly Detection in Imbalanced Credit Card Transactions using Hybrid PSO

Sivakumar¹,

Balasubramanian²

2016

IJCA

View full text Add to dashboard Cite

Anomaly detection is one of the major requirements of the current age that witnesses a huge increase in online transactions. Data imbalance also poses a huge challenge in the detection process. This paper presents a hybrid metaheuristic algorithm that performs effective anomaly detection on highly imbalanced data. Particle Swarm Optimization is used as the operating algorithm. This algorithm is hybridized by modifying the probabilistic selection using Simulated Annealing. A comparison study was carried out and it was observed that the simulated annealing based PSO showed much prominence when operated on both dominant and submissive data.

show abstract

Neural data mining for credit card fraud detection

Abstract: Abstract

Cited by 210 publications

References 5 publications

APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions

APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions

Overdue Prediction of Bank Loans Based on Deep Neural Network

Enhanced Anomaly Detection in Imbalanced Credit Card Transactions using Hybrid PSO

Contact Info

Product

Resources

About