A data mining based system for credit-card fraud detection in e-tail

Carneiro, Nuno Santos; Figueira, Gonçalo; Costa, Miguel

doi:10.1016/j.dss.2017.01.002

Cited by 209 publications

(97 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They found out that clustering algorithms Pam, Clara, Clarans and hierarchical algorithms such as Birch, Cure, Rock are the popular ones for financial fraud detection. Carneiro, Figueira, and Costa () examined the fraud problem by using real life data, an online retailer's transactions for four months, with different DM techniques.…”

Section: Data Mining Approaches To Financial Fraud Detectionmentioning

confidence: 99%

How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions

Esen

Bilgiç

Basdas³

2019

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Summary Only in the U.S. Stock Exchanges, the daily average trading volume is about 7 billion shares. This vast amount of trading shows the necessity of understanding the hidden insights in the data sets. In this study, a data mining technique, clustering based outlier analysis is applied to detect suspicious insider transactions. 1,244,815 transactions of 61,780 insiders are analysed, which are acquired from Thomson Financial, covering a period of January 2010–April 2017. In order to detect outliers, similar transactions are grouped into the same clusters by using a two‐step clustering based outlier detection technique, which is an integration of k‐means and hierarchical clustering. Then, it is shown that outlying transactions earn higher abnormal returns than non‐outlying transactions by using event study methodology.

show abstract

Section: Data Mining Approaches To Financial Fraud Detectionmentioning

confidence: 99%

How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions

Esen

Bilgiç

Basdas³

2019

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

show abstract

“…Several pieces of evidence (Carneiro, Figueira, & Costa, 2017;Cinca & Nieto, 2013;Jones et al, 2015;Lan, Hu, Patuwo, & Zhang, 2010;May, 2014) suggest that incorporating these costs into the financial prediction models can lead to better and more accurate results. Several pieces of evidence (Carneiro, Figueira, & Costa, 2017;Cinca & Nieto, 2013;Jones et al, 2015;Lan, Hu, Patuwo, & Zhang, 2010;May, 2014) suggest that incorporating these costs into the financial prediction models can lead to better and more accurate results.…”

Section: Cost Of Financial Decision Errorsmentioning

confidence: 99%

“…So as to determine the predicted status of a customer/corporation, this study considers the costs of FDSSs errors, type I and type II errors, and their impact on model selection. Several pieces of evidence (Carneiro, Figueira, & Costa, 2017;Cinca & Nieto, 2013;Jones et al, 2015;Lan, Hu, Patuwo, & Zhang, 2010;May, 2014) suggest that incorporating these costs into the financial prediction models can lead to better and more accurate results. It is obvious that the costs connected with type I error, Equation (14), (a customer/corporation having nondefault [healthy] credit is misclassified as having default credit/nonbankrupt) and type II error, Equation (15), (a customer/corporation with default [bankrupt] credit is misclassified as having nondefault [healthy] credit) are notably dissimilar.…”

Section: Cost Of Financial Decision Errorsmentioning

confidence: 99%

Topological applications of multilayer perceptrons and support vector machines in financial decision support systems

et al. 2018

View full text Add to dashboard Cite

The heart of this study is particularly on risk assessment of financial decision support systems (FDSSs), to advance the model performance and improve classification accuracy. To conquer the downsides of the classical models, statistical intelligence (SI) technologies, for example, multilayer perceptrons (MLPs) and support vector machines (SVMs), have been deliberated in FDSS applications. Recently, the prestigiousness of SI approaches has been confronted by the latest prediction learners. Therefore, to ensure the competitive performance of SI mechanisms, the current investigation scrutinizes the topological applications of MLPs and SVMs over eight different databases with equivalent combinations in credit scoring and bankruptcy predictions example sets. The experimental results reveal that MLP5‐5 and MLP4‐4, that is, the sigmoid activation function with five and four hidden layers, are the feasible topologies for the MLP algorithm, and on all databases in all performance criterions, SVM trained with the linear kernel function (SVM‐1) achieves better prediction results. From the “Baseline” family, random forest learner brings significant improvements in financial decisions. Lastly, FDSSs are found to be correlated with the nature of databases and the performance criterions of the trained algorithms. The results of this study, however, have practical and managerial implications to make a range of financial and nonfinancial strategies. With these contributions, therefore, our study not only supplements earlier evidence but also enhances the predictive performance of SI algorithms for financial decision support applications.

show abstract

“…Nuno Carneiro et.al [12] described the development and deployment of a fraud detection system in a large e-tail merchant. They investigated the combination of manual and mechanical classification gives insights into the full upgrading process and evaluates different machine learning methods.…”

Section: Literature Surveymentioning

confidence: 99%

An Approach to Detect Credit Card Frauds using Attribute Selection and Ensemble Techniques

Sharma¹,

Mittal²,

Geetika³

2018

IJCA

View full text Add to dashboard Cite

Managing of an account part is an essential area in our present day era where practically every human needs to manage the bank either physically or on the web Credit-card fraud prompts billions of dollars in misfortunes for online shippers. With the advancement of machine learning calculations, analysts have been finding progressively complex ways to identify extortion, yet handy usage is infrequently detailed. In this paper we are working to identify the fraudulent accounts using classification algorithms and then to improve the accuracy of results using feature selection technique. Bee search and genetic algorithms has been used to select relevant features from large dataset. The reduced dataset has been studied for different aspects. The ensemble learning techniques are implemented to reduce the variance. The impact of bagging, stacking and voting present the optimal technique for fraud detection.

show abstract

A data mining based system for credit-card fraud detection in e-tail

Cited by 209 publications

References 15 publications

How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions

How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions

Topological applications of multilayer perceptrons and support vector machines in financial decision support systems

An Approach to Detect Credit Card Frauds using Attribute Selection and Ensemble Techniques

Contact Info

Product

Resources

About