The fraudulent behavior of taxpayers impacts negatively the resources available to finance public services. It creates distortions of competition and inequality, harming honest taxpayers. Such behavior requires the go...The fraudulent behavior of taxpayers impacts negatively the resources available to finance public services. It creates distortions of competition and inequality, harming honest taxpayers. Such behavior requires the government intervention to bring order and establish a fiscal justice. This study emphasizes the determination of the interactions linking taxpayers with tax authorities. We try to see how fiscal audit can influence taxpayers’ fraudulent behavior. First of all, we present a theoretical study of a model pre established by other authors. We have released some conditions of this model and we have introduced a new parameter reflecting the efficiency of tax control;we found that the efficiency of a fiscal control have an important effect on these interactions. Basing on the fact that the detection of fraudulent taxpayers is the most difficult step in fiscal control, We established a new approach using DATA MINING process in order to improve fiscal control efficiency. We found results that reflect fairly the conduct of taxpayers that we have tested based on actual statistics. The results are reliable.展开更多
财务欺诈不仅会导致会计信息失真,还会危害经济的健康发展。因此,找到一种高效的智能化欺诈识别方法具有重要的现实意义。本文基于2020—2022年美国上市公司提交到EDGAR数据库的年度报告,聚焦于报告中管理层讨论与分析部分的文本信息(Ma...财务欺诈不仅会导致会计信息失真,还会危害经济的健康发展。因此,找到一种高效的智能化欺诈识别方法具有重要的现实意义。本文基于2020—2022年美国上市公司提交到EDGAR数据库的年度报告,聚焦于报告中管理层讨论与分析部分的文本信息(Management Discussion and Analysis,MD&A)并对其进行分析。考虑到现有数据中欺诈和非欺诈样本数据极度不平衡的特点,本文在分层注意力网络的基础上设计了一个更高效的财务欺诈识别模型,最终使得欺诈识别模型的F1分数和F2分数分别提高了4.1%和3.7%,所提出的算法框架能够有效提高非平衡MD&A文本数据集的分类正确率。研究结果为财务欺诈识别系统性能的提高以及其他领域长文本分类任务的预测提供了新的解决思路,并进一步验证了使用MD&A文本数据进行财务欺诈识别的有效性,为使用非平衡数据进行欺诈识别提供了直接的实证支持。展开更多
Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the verac...Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the veracity of the detection algorithms become critical to the deployment of a model that accurately scores fraudulent transactions taking into account case imbalance, and the cost of identifying a case as genuine when, in fact, the case is a fraudulent transaction. In this paper, a new criterion to judge classification algorithms, which considers the cost of misclassification, is proposed, and several undersampling techniques are compared by this new criterion. At the same time, a weighted support vector machine (SVM) algorithm considering the financial cost of misclassification is introduced, proving to be more practical for credit card fraud detection than traditional methodologies. This weighted SVM uses transaction balances as weights for fraudulent transactions, and a uniformed weight for nonfraudulent transactions. The results show this strategy greatly improve performance of credit card fraud detection.展开更多
文摘The fraudulent behavior of taxpayers impacts negatively the resources available to finance public services. It creates distortions of competition and inequality, harming honest taxpayers. Such behavior requires the government intervention to bring order and establish a fiscal justice. This study emphasizes the determination of the interactions linking taxpayers with tax authorities. We try to see how fiscal audit can influence taxpayers’ fraudulent behavior. First of all, we present a theoretical study of a model pre established by other authors. We have released some conditions of this model and we have introduced a new parameter reflecting the efficiency of tax control;we found that the efficiency of a fiscal control have an important effect on these interactions. Basing on the fact that the detection of fraudulent taxpayers is the most difficult step in fiscal control, We established a new approach using DATA MINING process in order to improve fiscal control efficiency. We found results that reflect fairly the conduct of taxpayers that we have tested based on actual statistics. The results are reliable.
文摘财务欺诈不仅会导致会计信息失真,还会危害经济的健康发展。因此,找到一种高效的智能化欺诈识别方法具有重要的现实意义。本文基于2020—2022年美国上市公司提交到EDGAR数据库的年度报告,聚焦于报告中管理层讨论与分析部分的文本信息(Management Discussion and Analysis,MD&A)并对其进行分析。考虑到现有数据中欺诈和非欺诈样本数据极度不平衡的特点,本文在分层注意力网络的基础上设计了一个更高效的财务欺诈识别模型,最终使得欺诈识别模型的F1分数和F2分数分别提高了4.1%和3.7%,所提出的算法框架能够有效提高非平衡MD&A文本数据集的分类正确率。研究结果为财务欺诈识别系统性能的提高以及其他领域长文本分类任务的预测提供了新的解决思路,并进一步验证了使用MD&A文本数据进行财务欺诈识别的有效性,为使用非平衡数据进行欺诈识别提供了直接的实证支持。
文摘Credit card fraudulent data is highly imbalanced, and it has presented an overwhelmingly large portion of nonfraudulent transactions and a small portion of fraudulent transactions. The measures used to judge the veracity of the detection algorithms become critical to the deployment of a model that accurately scores fraudulent transactions taking into account case imbalance, and the cost of identifying a case as genuine when, in fact, the case is a fraudulent transaction. In this paper, a new criterion to judge classification algorithms, which considers the cost of misclassification, is proposed, and several undersampling techniques are compared by this new criterion. At the same time, a weighted support vector machine (SVM) algorithm considering the financial cost of misclassification is introduced, proving to be more practical for credit card fraud detection than traditional methodologies. This weighted SVM uses transaction balances as weights for fraudulent transactions, and a uniformed weight for nonfraudulent transactions. The results show this strategy greatly improve performance of credit card fraud detection.
