Topological pattern discovery and feature extraction for fraudulent financial reporting

Huang, Shin‐Ying; Tsaih, Rua‐Huan; Yu, F. Richard

doi:10.1016/j.eswa.2014.01.012

Cited by 57 publications

(37 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, (1,0) refers to the lowest detection (Equation 11) performance. The area under ROC curve (AUROC), which is only applied for measuring the area under the curve, is adopted to assess a specific curve [50]. The best value for AUROC is 1.…”

Section: Evaluation Of the Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Detection Using Data Mining Methods in IT Systems: A Decision Support Application

Sönmez

Zontul

Kaynar

et al. 2018

Sakarya University Journal of Science

View full text Add to dashboard Cite

Although there are various studies on anomaly detection, effective and simple anomaly detection approaches are necessary as the inadequacy of appropriate ways for substantial network environments. In the existing analysis methods, it is seen that the methods of preliminary analysis are generally used, the extrapolations and probabilities are not taken into account and the unsupervised neural network (NN) methods are not used enough. As an alternative, the use of the Self-Organizing Maps has been preferred in the study. In other studies, analysis of data obtained from network traffic is analyzed, here, analysis of other information systems data and suggestions for alternative solutions are given, too. In addition, in-memory database systems have been used in practice in order to enable faster processing in analysis studies, due to the large size of data to be analyzed in large-scale network environments. An analysis of the application log data obtained from the management tools in the information systems was carried out. After anomaly detection results obtained and the verification test results are compared, it is found out that anomaly detection process is successful by 96%. The advantage offered for the company and users at IT and security monitoring processes is to eliminate the need for pre-qualification and to reduce the heavy workload. By this way, it is thought that a significant cost item is eliminated. It is also contemplated that the security vulnerabilities and problems associated with unpredictable issues will be detected through practice and thus many attacks and problems will be prevented in advance.

show abstract

Section: Evaluation Of the Resultsmentioning

confidence: 99%

“…Here, the threshold type binary classification algorithm was used by way of the efficacy simplicity, and experimentally controlled effect in the calculation [50]. It is, however, quite convenient to obtain ROC curves that simply evaluate the approaches that are being investigated by shifting the threshold value.…”

Section: Applicationmentioning

confidence: 99%

Anomaly Detection Using Data Mining Methods in IT Systems: A Decision Support Application

Sönmez

Zontul

Kaynar

et al. 2018

Sakarya University Journal of Science

View full text Add to dashboard Cite

show abstract

“…Previous studies have reported the superior classification performance of data mining techniques over traditional statistical methods [1][2][3][4][5][6][7][9][10][11][12][13][14][15][16][17][18][19][20]. The literature related to FFS detection driven by data mining techniques is presented in Table 1.…”

Section: Methodsmentioning

confidence: 99%

Detecting Fraudulent Financial Statements for the Sustainable Development of the Socio-Economy in China: A Multi-Analytic Approach

et al. 2019

View full text Add to dashboard Cite

Identifying financial statement fraud activities is very important for the sustainable development of a socio-economy, especially in China’s emerging capital market. Although many scholars have paid attention to fraud detection in recent years, they have rarely focused on both financial and non-financial predictors by using a multi-analytic approach. The present study detected financial statement fraud activities based on 17 financial and 7 non-financial variables by using six data mining techniques including support vector machine (SVM), classification and regression tree (CART), back propagation neural network (BP-NN), logistic regression (LR), Bayes classifier (Bayes) and K-nearest neighbor (KNN). Specifically, the research period was from 2008 to 2017 and the sample is companies listed on the Shanghai stock exchange and Shenzhen stock exchange, with a total of 536 companies of which 134 companies were allegedly involved in fraud. The stepwise regression and principal component analysis (PCA) were also adopted for reducing variable dimensionality. The experimental results show that the SVM data mining technique has the highest accuracy across all conditions, and after using stepwise regression, 13 significant variables were screened and the classification accuracy of almost all data mining techniques was improved. However, the first 16 principal components transformed by PCA did not yield better classification results. Therefore, the combination of SVM and the stepwise regression dimensionality reduction method was found to be a good model for detecting fraudulent financial statements.

show abstract

“…The study in [37] showed it is the way of extracting the proper traits from the transactions for constructing credit card fraud detection approach, by aggregating the transactions, and they expanded the transaction aggregation strategy, as proposed by creating a new group of properties according to the analysis of the time of the transaction by employing the "von Mises" distribution. Topological pattern in [38] discovered the 'topological patterns' of 'fraudulent financial reporting' FFR via dual 'GHSOM' ('Growing Hierarchical Self-Organizing Map') approach, as well as presenting an expert competitive feature extraction mechanism, which has been accurate in detecting the fraudulent and genuine by using the topological patterns for FFR and feature extraction. On the other hand, the authors in [39] proposed a linear discriminate as the fisher discriminant function to detect credit card fraud for the first time, their experiment which has been produced from the fisher discriminant function was more efficient for the fraudulent / genuine detection classifier.…”

Section: Credit Card Fraud Detectionmentioning

confidence: 99%

Comparative Analysis of Different Distributions Dataset by Using Data Mining Techniques on Credit Card Fraud Detection

2020

Teh. vjesn

View full text Add to dashboard Cite

Banks suffer multimillion-dollars losses each year for several reasons, the most important of which is due to credit card fraud. The issue is how to cope with the challenges we face with this kind of fraud. Skewed "class imbalance" is a very important challenge that faces this kind of fraud. Therefore, in this study, we explore four data mining techniques, namely naïve Bayesian (NB),Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Random Forest (RF), on actual credit card transactions from European cardholders. This paper offers four major contributions. First, we used under-sampling to balance the dataset because of the high imbalance class, implying skewed distribution. Second, we applied NB, SVM, KNN, and RF to under-sampled class to classify the transactions into fraudulent and genuine followed by testing the performance measures using a confusion matrix and comparing them. Third, we adopted cross-validation (CV) with 10 folds to test the accuracy of the four models with a standard deviation followed by comparing the results for all our models. Next, we examined these models against the entire dataset (skewed) using the confusion matrix and AUC (Area Under the ROC Curve) ranking measure to conclude the final results to determine which would be the best model for us to use with a particular type of fraud. The results showing the best accuracy for the NB, SVM, KNN and RF classifiers are 97,80%; 97,46%; 98,16% and 98,23%, respectively. The comparative results have been done by using four-division datasets (75:25), (90:10), (66:34) and (80:20) displayed that the RF performs better than NB, SVM, and KNN, and the results when utilizing our proposed models on the entire dataset (skewed), achieved preferable outcomes to the under-sampled dataset.

show abstract

Topological pattern discovery and feature extraction for fraudulent financial reporting

Cited by 57 publications

References 37 publications

Anomaly Detection Using Data Mining Methods in IT Systems: A Decision Support Application

Anomaly Detection Using Data Mining Methods in IT Systems: A Decision Support Application

Detecting Fraudulent Financial Statements for the Sustainable Development of the Socio-Economy in China: A Multi-Analytic Approach

Comparative Analysis of Different Distributions Dataset by Using Data Mining Techniques on Credit Card Fraud Detection

Contact Info

Product

Resources

About