Detecting evolutionary financial statement fraud

With the prevalence of Internet AI technology, financial fraud becomes an imperative problem, especially in the context of machine learning. Technologies such as deep learning and natural language processing provide effective tools for detecting fraud with the guidance of financial statements, improving the efficiency and accuracy of data analysis, and helping to ensure financial safety. In this study, we propose a sophisticated representation learning method to detect financial statement fraud by tracking the detailed changes in the company’s Management Discussion and Analysis (MD&A) documents over time. Unlike traditional word frequency methods, we align paragraphs between consecutive disclosures based on their similarity at the paragraph level and categorize them into three types: added, deleted, and matched. Next, we create multivariate change trajectory representations based on fraud-related word categories. Finally, we use these word-level change trajectories to design a fraud detection model and compare it with several traditional models as well as the latest Time-Series Foundation Models. Experiments on 24 years of financial report data, from 1995 to 2019, show that our representation learning method significantly improves the performance of financial statement fraud detection across 11 different machine learning models, consistently outperforming traditional word frequency methods. Our method opens a new paradigm for feature engineering in financial statement fraud detection. Our code can be found at https://github.com/LittelStudent/Financial-Statement-Fraud-Detection-ParaEmb-FraudW2V .

Financial statement fraud is a discrepancy between the application of accounting principles and the preparation of financial statements with the aim of deceiving and deceiving users of financial statements. The approach taken to identify the factors that influence financial statement fraud, one of which is the fraud hexagon model. There are six factors in the fraud hexagon, namely Stimulus which will be represented by financial targets, Ability will be represented by a change of director, Collusion will be represented by political connections, Opportunity will be represented by the quality of external auditors, Rationalization will be represented by audit opinion and Ego is represented by many photos CEO. This study aims to analyze the effect of the fraud hexagon on fraudulent financial statements in infrastructure, utility and transportation sector companies listed on the Indonesia Stock Exchange in 2015-2019. Detection of the possibility of fraudulent financial statements is measured by the F-Score model. This study uses a purposive sampling technique with a sample of 25 companies and 125 data on annual reports and financial statements. The results showed that financial targets, the quality of external auditors, and the number of CEO photos had no effect on financial statement fraud, while the change of directors had a negative and significant effect on financial statement fraud, political connections had a positive and significant effect on financial statement fraud. Audit opinion has a negative and significant effect on financial statement fraud.

The study examines conceptually the detection of financial statements fraud using fraud pentagon. The study discusses the relationship between fraud pentagon and financial statement fraud. The methodology adopted in this study is library research whereby relevant and extant literature related to the elements in fraud pentagon were reviewed in relation to financial statements fraud. In the search for literature, it was observed that the various elements of fraud pentagon such as pressure (financial targets, financial stability, institutional ownership and external pressure), opportunity (ineffective monitoring and nature of industry), rationalization (auditor switching and change of director), competence (the changes in the company directorship and the proportion of independent directors in the board) and arrogance (frequent number of CEO's picture and CEO duality) significantly affect financial statements fraud. This study recommends that fraud pentagon should be given the statutory support in order to address financial statements fraud.
 
 Received: 27 August 2023 / Accepted: 19 October 2023 / Published: 5 November 2023

Objective: Financial fraud has been a big concern for many organizations across industries; billions of dollars are lost yearly because of this fraud. So businesses employ data mining techniques to address this continued and growing problem. This paper aims to review research studies conducted to detect financial fraud using data mining tools within one decade and communicate the current trends to academic scholars and industry practitioners. Method: Various combinations of keywords were used to identify the pertinent articles. The majority of the articles retrieved from Science Direct but the search spanned other online databases (e.g., Emerald, Elsevier, World Scientific, IEEE, and Routledge - Taylor and Francis Group). Our search yielded a sample of 65 relevant articles (58 peer-reviewed journal articles with 7 conference papers). One-fifth of the articles was found in Expert Systems with Applications (ESA) while about one-tenth found in Decision Support Systems (DSS). Results: 41 data mining techniques were used to detect fraud across different financial applications such as health insurance and credit card. Logistic regression model appeared to be the leading data mining tool in detecting financial fraud with a 13% of usage.In general, supervised learning tool have been used more frequently than the unsupervised ones. Financial statement fraud and bank fraud are the two largest financial applications being investigated in this area – about 63%, which corresponds to 41 articles out of the 65 reviewed articles. Also, the two primary journal outlets for this topic are ESA and DSS. Conclusion: This review provides a fast and easy-to-use source for both researchers and professionals, classifies financial fraud applications into a high-level and detailed-level framework, shows the most significant data mining techniques in this domain, and reveals the most countries exposed to financial fraud.

Financial statement fraud is an intentional misstatements, omissions or disclosure in financial statement done by an individual or a party to mislead financial statement users when making decisions. Financial statement fraud committed by irresponsible parties for their own advantage can lead to long-term losses. The purpose of this study is to examine the effects of fraud pentagon theory for detecting financial statement fraud in banking companies listed in the Indonesia Stock Exchange for 2020-2022 period. This study was analysed using multiple regression research method which processed using SPSS 25. The data used in this study was secondary data from financial statement and annual reports. This study used purposive-sampling technique with sample of 90 data observations. The results of this study shows that financial stability and changes in auditor have a significant and negative effect on financial statement fraud. Meanwhile external pressure, monitoring effectiveness, changes in director, and frequent number of CEO’s picture in annual report have no significant effects on financial statement fraud.

Financial statement fraud has been a serious concern for many investors and other stakeholders, and this motivated many researchers in developing traditional regression analysis in order to detect financial statement fraud. Intelligent financial statements fraud detection systems were continuously developed to uncover any potential for fraud signals which could assist the stakeholders in taking their decisions. This study reviews and identifies the gaps in the previous studies that tested financial statement fraud detection using data mining techniques. The study expands the knowledge of this research topic among researchers, forensic accountants, auditors and regulators and provides organizations with useful information regarding the various types of financial fraud and data mining techniques available.

This study aims to analyze the influence of the fraud Pentagon elements on detecting financial statement fraud in BUMN listed on the Indonesia Stock Exchange (IDX) for 2020-2022. The study population was all state-owned enterprises BUMN listed on the Indonesia Stock Exchange. The sample was selected using a purposive sampling method, resulting in 18 companies. Data analysis used multiple regression analysis. The results showed that financial stability and personal financial needs were proven to have no significant effect on financial statement fraud. Financial targets, changes in director and auditor, and the number of CEO photos in the annual report showed a significant positive effect on financial statement fraud. Meanwhile, ineffective monitoring and dualism positions showed a significant negative effect. These findings indicate that several elements in the fraud pentagon framework significantly affect financial statement fraud in BUMN in Indonesia, with the model explaining 62.6% of the variance in fraud detection. ABSTRAK Penelitian ini bertujuan menganalisis pengaruh elemen fraud pentagon terhadap pendeteksian kecurangan laporan keuangan pada BUMN yang terdaftar di Bursa Efek Indonesia (BEI) periode 2020-2022. Populasi penelitian adalah seluruh badan usaha milik negara BUMN yang terdaftar pada Bursa Efek Indonesia. Sampel dipilih menggunakan purposive sampling method sehingga sejumlah 18 perusahaan. Analisis data menggunakan analisis regresi berganda. Hasil penelitian menunjukkan financial stability dan personal financial needs terbukti tidak berpengaruh signifikan terhadap kecurangan laporan keuangan. Financial targets, change in director, change in auditor, dan jumlah foto CEO dalam laporan tahunan menunjukkan pengaruh positif signifikan terhadap kecurangan laporan keuangan. Sementara itu, ineffective monitoring dan dualism position menunjukkan pengaruh negatif signifikan. Temuan ini mengindikasikan bahwa beberapa elemen dalam kerangka fraud pentagon secara signifikan mempengaruhi kecurangan laporan keuangan pada BUMN di Indonesia, dengan model menjelaskan 62,6% varians dalam pendeteksian fraud.

This study aims to examine the influence of external pressure, financial target, ineffective monitoring, rationalization, and capability on financial statement fraud. Financial Statement Fraud is measured by earnings management using discretionary accruals. This study uses secondary data were taken from the manufacturing companies which are listed in Indonesian Stock Exchange. Sample selection is done by purposive sampling method and sample obtained from this research were 45 of a total 135 companies. Method of analysis used multiple linear regression analysis. The result show that simultanoeusly of external pressure, financial target, ineffective monitoring, rationalization, and capability have a significant influence on financial statement fraud. Partially, external pressure, financial target, rationalization, and have no significant influence on financial statement fraud. Ineffective monitoring partially has a significant influence on financial statement fraud.

Financial statement fraud can result in significant losses for stakeholders including investors, creditors, and the government. As a result, the auditor is crucial in identifying and stopping such fraud. The auditor's professional skepticism and sense of self-efficacy are two aspects that might affect their capacity to spot fraud. Among the firms listed on the Indonesia Stock Exchange, this study intends to investigate the impact of professional skepticism and self-efficacy on identifying financial statement fraud. A total of 147 respondents participated in the quantitative research approach, which employed a purposive sample strategy. Data was gathered through questionnaires delivered to respondents who participated in the company's auditing procedure. A multiple linear regression analysis was used to examine the data that had been gathered. The study's findings indicate a substantial relationship between professional skepticism and self-efficacy and the ability to identify financial statement fraud. Identifying financial statement fraud is specifically positively and significantly impacted by professional skepticism and self-efficacy. These findings can significantly contribute to practitioners' and academics' abilities to identify situations of fake financial statement.

Financial fraud hasattracted the attentions of researchers because it concerns with many different market participants. The fraudulent firms provide misleading information in the financial reports in order to achieve unethical goals. Investors can suffer losses if they use such information to make decisions. Therefore, it is important to detect fraud in financial statements. This paper includes two parts: Part I talks about the motivations and influences of financial frauds. Part II talks about how to detect financial fraud in the financial statements.

This study aims to examine the influence of fraud hexagon theory factors on financial statement fraud in transportation and logistics sector companies listed on the Indonesia Stock Exchange from 2018 to 2022. The fraud hexagon theory elements in this study are proxied by financial targets, ineffective supervision, auditor changes, board of directors changes, frequency of CEO photo appearances, and State-Owned Enterprises. The sample in this study was 19 companies that had been selected using purposive sampling techniques. The number of observations in this study was 95 observations. The data analysis carried out in the study was panel data regression analysis using EViews 12 software as a data analysis tool. The results of the analysis showed that financial targets had a positive effect on financial statement fraud. However, ineffective supervision, auditor changes, board of directors changes, frequency of CEO photo appearances, and state-owned enterprise variables were shown to have no effect on financial statement fraud. This study provides theoretical implications in the form of additional information about the influence of financial targets on financial statement fraud and this study also provides practical implications for company leaders to pay more attention and consider the company's financial targets as one of the indicators that can be used to detect financial statement fraud.

As the monetary cost of fraud escalates globally, and the ensuing confidence in financial markets deteriorates, the international demand for quality in financial statements intensifies. But what constitutes quality in financial statements? This book examines financial statement fraud, a topical and increasingly challenging area for financial accounting, business, and the law. Evidence shows that accounting anomalies in an organization’s financial statements diminish the quality and serviceability of financial information. However, an anomaly does not necessarily signal fraud. Financial statement fraud is intended to mislead shareholders and other stakeholders. In this book, elements that underpin diversity of accounting anomalies likely found in fraudulent financial accounting statements are revealed. Multiple research methods are used in the analysis of selected international fraud cases, each illustrating examples of financial statement fraud, including: revenue recognition, overstatement and/or misappropriation of assets, understatement of expenses and liabilities, disclosure fraud, bribery and corruption. Additionally, the phoenix phenomenon with regard to fraud in financial accounting is investigated. Drawing on documented observations of commercial and legal cases globally this study highlights the necessity for continued development of financial audit practices and other audit services.

Financial statements are a medium to provide useful information for stakeholders and parties involved. Correct information will help all parties to make the right decisions in carrying out economic or business activities. Fraud is common in the financial and non-financial industries today. Fraud in the financial industry is commonly referred to as financial statement fraud. Up to the third quarter of 2018, 36 banks indicated the occurrence of fraud. This study aims to examine the fraud triangle factor in detecting financial statement fraud. The object of this study uses 43 banking companies listed on the Indonesia Stock Exchange period 2015-2019. Analysis data was using panel regression analysis. The results show there is a significant relationship between financial stability and the rationalization of financial statement fraud. Meanwhile, financial targets, external pressure, and ineffective monitoring did not have a significant effect on financial statement fraud.

The purpose of this study is to analyze the detection financial statement fraud using fraud diamond perspective. The variable in this study consists of financial statement fraud as dependent variable and fraud diamond such as financial target, financial stability, monitoring effectiveness, nature of industry, auditor change, and director change as the independent variables. This study used purposive sampling on manufacturing company listed in the Indonesia Stock Exchange from 2018-2020 period with a total observation of 166 sample. Multiple linear regression is used to analyze the use of fraud diamond on detecting financial statement fraud. The research finds that nature of industry, and financial stability have significant effect on financial statement fraud. Contrarily, variables such as financial target, monitoring effectiveness, auditor change, and director change have no significant effect on financial statement fraud. Thus, only nature of industry, and financial stability can be used to detect financial statement fraud.Â

The rise of financial statement fraud is currently the basis for research conducted. Companies often use financial statement fraud schemes. These show how important it is to check on a business' health often and take corrective measures if necessary. Falsifying financial accounts is a common practice among businesses to give the impression that everything is fine when it is not. The purpose of this study is to estimate and analyze how financial stability and financial distress impact financial statement fraud. The investigation will encompass all manufacturing businesses listed on the Indonesia Stock Exchange between 2020 and 2022. Based on the results of the purposive sampling method, We used a sample size of 35 companies for the study, which equates to about 105 sample data will be observed for three years, from 2020 to 2022. After that, multiple linear regression is used to analyze the data. This study contributes to the increasing body of data indicating the incidence of fraudulent accounting is not the same in times of economic boom and bust. This research shows that financial stability has not a deleterious effect on the likelihood of financial statement fraud and financial distress significantly and positively affects financial statement fraud.. The implication to the research, it is crucial for businesses to adopt preventive measures and to ascertain early on whether they are healthy or not in order to avoid making false financial statements.