Financial reports provide information about a company's assets, liabilities, equity, income, expenses and cash flow. This information can be used by various parties such as investors, creditors, government and management to make business decisions and assess company performance. Companies in obtaining good financial reports need to detect fraudulent financial statements first. Financial statement fraud can be detrimental to investors and creditors because it gives a wrong picture of a company's financial performance. This study aims to examine the effect of big data competence and the tone of the top internal auditors on the detection of financial statement fraud, as well as to mediate the effect of big data competence on the detection of financial statement fraud through self-efficacy. This research uses a sample of 183 respondents who are internal auditors in companies in Indonesia. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results of the study show that big data competence has no significant effect on the detection of financial statement fraud, but has a positive and significant effect on self-efficacy. In addition, the internal auditor's tone of the top also has a positive and significant effect on the detection of financial statement fraud. Finally, self-efficacy partially mediates the relationship between big data competence and fraud detection of financial statements. This research provides important implications for practitioners and decision makers in developing internal auditor competence in the field of big data and paying attention to tone of the top as an important factor in detecting fraudulent financial statements. In addition, this research also contributes to strengthening the understanding of the relationship between big data competence, tone of the top, self-efficacy, and fraud detection of financial statements in the Indonesian context.

Detecting credit card fraud is a major challenge because fraudulent transactions represent only a small fraction of financial data. Traditional methods like SMOTE (Synthetic Minority Oversampling Technique) help balance datasets but can also introduce noise and make models over- fit, reducing their effectiveness. To tackle the issues that come with oversampling, we present the Enhanced Fraud Classifier with Tomek Links (EFC-Tomek) framework. This approach builds on the existing EFN-SMOTE but takes a different approach, using Tomek Links undersampling instead of SMOTE oversampling to balance the dataset. Our main goal is to improve data quality and enhance the model’s ability to detect fraud more accurately and effectively. To test EFC- Tomek, we used two real-world datasets: European cardholders and Loan Prediction. We evaluated its performance using a number of classifiers, such as Random Forest, eXtreme Gradient Boosting, Logistic Regression, Gradient Boosting, Artificial Neural Networks, and Support Vector Classifier. The results showed that EFC-Tomek improved fraud detection, with ANN achieving the highest accuracy on both datasets.

This paper aims to analyze the capability of advanced AI as a predictor of audit quality with particular reference to auditors in Kuwait. The research focuses on understanding the role of advanced AI technologies in the improvement of most audit activities around risk, fraud, and compliance. In order to classify the Kuwaiti auditors into different segments on the basis of their internet usage, both the quantitative data collected through a questionnaire survey is used with additional data collected from structured interviews with them. The results are expected to offer a rich and detailed account of the pragmatic opportunities and difficulties of applying AI in audits while highlighting its potential of reshaping conventional approaches. This study contributes relevant knowledge regarding the audit quality and governance garnered from linking theory and practice, providing the feasible recommendations for auditors and policymakers in the member countries of the GCC.

In the realm of financial security, the detection and prevention of credit card fraud has become paramount. With the ever-increasing reliance on digital transactions, the risk of fraudulent activities targeting credit card systems has grown significantly. To combat this, sophisticated techniques are required to swiftly identify and mitigate potential threats. Machine learning, a cornerstone of modern data analysis, has emerged as a powerful tool in this pursuit. By leveraging vast datasets and employing advanced algorithms, machine learning enables the automated scrutiny of transactions, distinguishing between legitimate and fraudulent activities with remarkable precision. This paper introduces an intelligent method for credit card fraud detection that relies on Competitive Swarm Optimization (CSO) and Random Weight Network (RWN). Additionally, the system includes an automated hybrid feature selection capability to identify the most pertinent features during the detection process. The experimental outcomes validate that this system can attain outstanding results in G-Mean, RUC, and Recall values.

This study aims to identify the determinants of the expectation gap in fraud detection between internal auditors and bankers in Indonesia. The shift in the internal audit task in the banking sector can cause the hole in audit expectations to widen. This research uses qualitative methods with an interpretive paradigm which is rarely done by previous research. The results of interviews with internal audit work units and bank managers from 4 state-owned and private banks indicate a gap in audit expectations regarding the responsibilities between internal auditors and bankers, especially in carrying out the function of examining and detecting fraud. This study recommends the financial services authorities and bank leaders be able to improve education regarding anti-fraud policies to stakeholders, especially in terms of a clear division of tasks in fraud detection in the banking sector.