Detecting financial statement fraud using dynamic ensemble machine learning

Our study uses Machine learning to develop an advanced fraud detection model that can detect fraudulent firms. We build our model using raw financial and non-financial variables following prior literature. In addition, we introduce the Dynamic Ensemble Selection algorithm to the fraud detection literature, which combines individual classifiers dynamically to make a final prediction. Using several performance evaluation metrics, we find that our model can outperform several machine learning models used in recent studies.     

Understanding the potential impact of information technology on the susceptibility of organizations to fraudulent employee behavior

Although the infusion of progressively advanced information technology (IT) into business organizations can improve the capturing, processing, and reporting of critical decision-making information across the enterprise, such technology can also create an environment that is more vulnerable to fraud. In this article, we develop a framework based on the theory of planned behavior [Org. Behav. Human Decis. Process. 50 (2)(1991) 179] that addresses the potential impact of IT on the susceptibility of an organization to employee fraud. We believe that this framework can serve as a useful tool for management, internal auditors, and external auditors when assessing fraud risk.     

审计师变更与审计质量:一个理论分析

本文通过建立股东、管理层和审计师三方参与的两委托人-单代理人博弈模型,研究了固定审计费用下不同审计师变更方式对审计质量的影响。研究结果表明,审计师强制性单期变更与审计师强制性定期变更下,审计师与管理层之间的合谋将导致严重的财务舞弊;而在审计师自愿性变更下,股东可以利用解聘现任审计师这一威胁来阻止审计师和管理层之间的合谋,使得审计师和管理层的最优策略均为真实披露公司的盈余信息,并发表标准无保留审计意见。     

税费整合的动因及主要内容探析

税费整合涉及国家经济结构及税费体制的变革,旧体制下的税费结构严重影响着分配效率。本文对我国部分税费整合的可行性做了初步的分析和探索,以期为我国税费整合的实践提供参考。     

内部控制信息披露经济后果实证研究

2002年《萨班斯法案》颁布实施以来,内部控制信息披露作为预防舞弊保护投资者利益的重要制度安排,受到世界各国证券监管部门的重视.我国要求2011年起境内外同时上市公司全面披露内部控制信息,2012年起两大交易所主板上市公司强制披露内控信息.研究发现披露内部控制鉴证报告的样本公司支付的审计费用更高,而是否披露内部控制自我评价报告及是否披露内部控制缺陷与审计费用变化不存在显著关系.研究结论提供了我国内部控制信息披露制度在审计领域引发经济效果的客观证据,同时发现与验证了新制度环境下影响上市公司支付审计费用变化的新的重要影响因素.     

Financial statement comparability and accounting fraud

We examine the association between financial statement comparability and the likelihood of accounting fraud. Prior research documents a negative association between the quality of a firm's reporting environment and accounting fraud. We build on this literature and show that poor financial statement comparability is associated with a greater likelihood of accounting fraud. We also find that accounting comparability declines over time as the year of fraud detection approaches and that the association between comparability and fraud becomes more negative over this time. In addition, we find that financial statement comparability improves after fraud detection, consistent with the notion that managers improve their financial reporting quality after fraud.     

Predicting fraud by investment managers

We test the predictability of investment fraud using a panel of mandatory disclosures filed with the SEC. We find that disclosures related to past regulatory and legal violations, conflicts of interest, and monitoring have significant power to predict fraud. Avoiding the 5% of firms with the highest ex ante predicted fraud risk would allow an investor to avoid 29% of fraud cases and over 40% of the total dollar losses from fraud. We find no evidence that investors receive compensation for fraud risk through superior performance or lower fees. We examine the barriers to implementing fraud prediction models and suggest changes to the SEC's data access policies that could benefit investors.     

A Multi-Line Insurance Fraud Recognition System: A Government-Led Approach in Korea

This article introduces a government-led insurance fraud detection program in Korea. The Insurance Fraud Recognition System (IFRS) uses policy and claims data from multi-lines of insurance (life, automobile, and fire), employs a three-stage statistical and link analysis to identify presumably fraudulent claims by claimant or by group, and generates system reports that the government regulator draws on to make decisions. The authors evaluate the system based on the fraud statistics and IFRS results for 2004, and offer recommendations for system improvement. This article examines existing studies about fraud, industry experiments using advanced technology, and government assistance to the insurance industry's fight against fraud in selected countries. It also provides a brief overview of the Korean insurance market, especially after the recent Asian economic crisis.     

The relation between earnings management and financial statement fraud

This paper provides new evidence on the characteristics of firms that commit financial statement fraud. We examine how previous earnings management impacts the likelihood that a firm will commit financial statement fraud and in doing so develop three new fraud predictors. Using a sample of 54 fraud and 54 non-fraud firms, we find that fraud firms are more likely to have managed earnings in prior years and that earnings management in prior years is associated with a higher likelihood that firms that meet or beat analyst forecasts or that inflate revenue are committing fraud. We further find that fraud firms are more likely to meet or beat analyst forecasts and inflate revenue than non-fraud firms are even when there is no evidence of prior earnings management. This paper contributes to the fraud detection literature and the earnings management literature, and can help practitioners and regulators develop better fraud detection models.     

Booms, Busts, and Fraud

Firms sometimes commit fraud by altering publicly reported informationto be more favorable, and investors can monitor firms to obtainmore accurate information. We study equilibrium fraud and monitoringdecisions. Fraud is most likely to occur in relatively goodtimes, and the link between fraud and good times becomes strongeras monitoring costs decrease. Nevertheless, improving businessconditions may sometimes diminish fraud. We provide an explanationfor why fraud peaks towards the end of a boom and is then revealedin the ensuing bust. We also show that fraud can increase iffirms make more information available to the public.     

Versicherungsbetrug aus vertragstheoretischer Sicht

Insurance fraud is a significant economic problem. Following the deregulation of the German insurance market in 1994, contractual features are now possible which were previously restricted. Therefore, there is a need to analyse the insurance fraud reduction potential of this instrument. This paper investigates three forms of insurance fraud: ?Costly State Verification“, ? Costly State Falsification“ and third party fraud. Consequences for the optimal contractual design are deduced.     

论诈骗罪既遂认定的标准及其具体应用

诈骗罪是多发性犯罪,司法实践中又常有争议。本文针对认定诈骗罪既遂与未遂各标准之要点,结合诈骗罪犯罪构成及罪质特征进行剖析,得出"失控说"为区别诈骗罪既遂与未遂之标准的合理性和必要性。并以此为基础,具体分析了几个实务中易产生分歧的案例,以期能在司法操作中统一认识、罚当其罪。     

舞弊治理：基于上市公司财务舞弊特征的分析

选取2003～2007年度5645家沪深两地上市公司为样本,首先对其中209家舞弊公司财务舞弊的影响因素做统计分析,明晰上市公司财务舞弊的特征;然后,根据舞弊公司不同特征进一步实证检验,得出大规模事务所的选择、股权集中度、公司规模与财务舞弊负相关,独立董事比例与财务舞弊成"U"型关系,但没有发现代表财务状况指标净资产收益率的显著性影响,究其原因,发现舞弊公司存在虚增利润以外的其他更多隐性盈余操纵手段.     

BEYOND THE NUMBERS: MINING THE ANNUAL REPORTS FOR HIDDEN CUES INDICATIVE OF FINANCIAL STATEMENT FRAUD

Unlike previous fraud detection research, a vast majority of which has focused primarily on the use of quantitative financial information to predict fraud, in this study we examine qualitative textual content in annual reports to predict fraud and see whether there are discernible differences in the writing and presentation style between companies that committed fraud and those that did not. We believe that while numeric financial information in the annual reports can hide details of fraud, textual information relating to writing and presentation styles in such reports provides valuable clues pertaining to the existence of fraud. In this study we use the chi‐square test to analyse our data and test hypotheses about predictors of fraud that may explain linguistic feature variations in fraudulent and nonfraudulent annual reports. We provide new results on the usefulness of the qualitative content of annual reports in detecting fraud. Copyright © 2012 John Wiley & Sons, Ltd.     

Is There a Link between Executive Equity Incentives and Accounting Fraud?

We compare executive equity incentives of firms accused of accounting fraud by the Securities and Exchange Commission (SEC) during the period 1996–2003 with two samples of firms not accused of fraud. We measure equity incentives in a variety of ways and employ a battery of empirical tests. We find no consistent evidence that executive equity incentives are associated with fraud. These results stand in contrast to assertions by policy makers that incentives from stock‐based compensation and the resulting equity holdings increase the likelihood of accounting fraud.     

What drives mortgage fees in Australia?

We investigate the factors that affect total, ongoing and origination fees of mortgages in Australia during the period 1996 to 2011. We find that banks charge significantly higher total and ongoing fees than mortgage corporations although they require lower origination fees. We also find that fee levels are dependent on loan size, loan‐to‐value ratio and loan features like term of the loan and presence of an offset account. Further, we confirm that lenders trade‐off higher (lower) interest rates with lower (higher) fee levels. Finally, our results show that mortgage fees are significantly affected by market conditions.     

Corporate fraud culture: Re‐examining the corporate governance and performance relation

We analyse the corporate governance and performance relation, when conditioning on corporate fraud, for fraud firms during 2000 – 2007. Fraud firms are identified as either self‐ reported fraud events, or subject to regulatory investigation. We use the inverse Mills ratio procedure to account for firms' (unobservable) fraud culture in the dynamic system GMM model of the performance‐ governance relation. We find that corporate governance is an endogenously determined characteristic that has no causal impact on firm performance when conditioning on fraud. Fraud is a significant regulatory event but its overall economic impact at the firm level is highly variable.     

Go before the whistle blows: an empirical analysis of director turnover and financial fraud

This study investigates whether outside directors are aware of financial fraud. Our analysis focuses on the abnormal turnover of these directors during the fraud committing period, before fraud is discovered and before lawsuits are filed. Our empirical analysis shows that, during the fraud committing period, outside directors in fraud firms exhibit an abnormal level of turnover. Examining the characteristics of outside directors and boards at these fraud firms, we find strong evidence that female directors, directors who have greater stock ownership in the firm, and directors with multiple directorships at other firms are more likely to depart fraud firms. We also find some evidence that board size, number of meetings, and fraction of financial experts are related to abnormal turnover in fraud firms during the fraud committing period. We show that abnormal director turnover is significantly higher for fraud that is considered more egregious (i.e., involving fictitious transactions and disclosure problems). Lastly, directors are more likely to depart fraud firms with more serious fraud, as proxied by higher ex-post settlement amounts and longer fraud duration.     

Industry informational interactions and corporate fraud

We examine three information channels through which product market interactions in an industry can affect firms' incentives to misreport financial information to investors. We find that lower product market sensitivity to individual firms' information and greater use of relative performance evaluation encourage the commission of financial fraud. Industry structures that give rise to less collection of information about individual firms decrease the probability of fraud detection and increase the probability of fraud commission. We also examine dynamic effects of fraud. Our results suggest that, in fragmented industries, fraud can amplify cyclical fluctuations in the real economy.     

Using Nonfinancial Measures to Assess Fraud Risk

This study examines whether auditors can effectively use nonfinancial measures (NFMs) to assess the reasonableness of financial performance and, thereby, help detect financial statement fraud (hereafter, fraud). If auditors or other interested parties (e.g., directors, lenders, investors, or regulators) can identify NFMs (e.g., facilities growth) that are correlated with financial measures (e.g., revenue growth), inconsistent patterns between the NFMs and financial measures can be used to detect firms with high fraud risk. We find that the  difference  between financial and nonfinancial performance is significantly greater for firms that committed fraud than for their nonfraud competitors. We also find that this difference is a significant fraud indicator when included in a model containing variables that have previously been linked to the likelihood of fraud. Overall, our results provide empirical evidence suggesting that NFMs can be effectively used to assess fraud risk.