Explore the vast range of titles available.

Credit fraud observations are minority in the sample set, variables tend to be seriously unbalanced, and the prediction results tend to be biased towards more observed classes. Common resolution usually constructs 1:1 data, either cutting off part of more classes (undersampling) or reducing classes for bootstrap sampling (oversampling). XGBoost is an efficient system implementation of Gradient Boosting, and also GB algorithm based on CART. Based on the real online transaction data of an Internet financial institution, this paper studies the performance of XGBoost algorithm on the original data set, the undersampling and SMOTE data sets respectively.

Following the 2016 US presidential election, many have expressed concern about the effects of false stories (“fake news”), circulated largely through social media. We discuss the economics of fake news and present new data on its consumption prior to the election. Drawing on web browsing data, archives of fact-checking websites, and results from a new online survey, we find: 1) social media was an important but not dominant source of election news, with 14 percent of Americans calling social media their “most important” source; 2) of the known false news stories that appeared in the three months before the election, those favoring Trump were shared a total of 30 million times on Facebook, while those favoring Clinton were shared 8 million times; 3) the average American adult saw on the order of one or perhaps several fake news stories in the months around the election, with just over half of those who recalled seeing them believing them; and 4) people are much more likely to believe stories that favor their preferred candidate, especially if they have ideologically segregated social media networks.

This paper introduces an information system based on SpringBoot framework of man hour management, by analysing the problems existing in the man hour management workflow and process in an industrial design and assembly company. Like fraud timesheet, confusion of validation, etc. This paper designs the different function modules and provides the overview of the system, and explains the reason of using SpringBoot framework. Finally, describe the improvement for the company in both controlling and processing level.

Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. Here we argue that this necessitates a broad scientific research agenda to study machine behaviour that incorporates and expands upon the discipline of computer science and includes insights from across the sciences. We first outline a set of questions that are fundamental to this emerging field and then explore the technical, legal and institutional constraints on the study of machine behaviour. Understanding the behaviour of the machines powered by artificial intelligence that increasingly mediate our social, cultural, economic and political interactions is essential to our ability to control the actions of these intelligent machines, reap their benefits and minimize their harms.

Consumer reviews are now part of everyday decision making. Yet the credibility of these reviews is fundamentally undermined when businesses commit review fraud, creating fake reviews for themselves or their competitors. We investigate the economic incentives to commit review fraud on the popular review platform Yelp, using two complementary approaches and data sets. We begin by analyzing restaurant reviews that are identified by Yelp’s filtering algorithm as suspicious, or fake—and treat these as a proxy for review fraud (an assumption we provide evidence for). We present four main findings. First, roughly 16% of restaurant reviews on Yelp are filtered. These reviews tend to be more extreme (favorable or unfavorable) than other reviews, and the prevalence of suspicious reviews has grown significantly over time. Second, a restaurant is more likely to commit review fraud when its reputation is weak, i.e., when it has few reviews or it has recently received bad reviews. Third, chain restaurants—which benefit less from Yelp—are also less likely to commit review fraud. Fourth, when restaurants face increased competition, they become more likely to receive unfavorable fake reviews. Using a separate data set, we analyze businesses that were caught soliciting fake reviews through a sting conducted by Yelp. These data support our main results and shed further light on the economic incentives behind a business’s decision to leave fake reviews. This paper was accepted by Lorin Hitt, information systems .

Corporate financial scandals like WorldCom, Parmalat, Enron, Polypeck, and Guinness, are strongly associated with questionable accounting and auditing practices. The literature has been enriched by many studies aiming to understand why people are able to commit fraud and their motivations. The Fraud Triangle Theory and Fraud Diamond Theory identify elements that lead people to commit fraud. Pressure, motivation or opportunity, rationalization, and capability are the main categories of indicators or red flags tracked by auditors to prevent or detect fraud. However, the multiplication of models and theories is unsatisfactory for auditors and more adequate research to help them deal with fraud is required. At the same time, the literature considers fraud as one of the fundamental reasons for the Greek crisis. Even if in recent years, a large-scale effort to prevent and detect fraud has been undertaken, it seems that only the perception of fraud is changing. One of the key elements of fraud in Greece is its tendency to involve cultural factors that influence behavior. The purpose of this article is to help Greek auditors better apply the fraud triangle by considering this specific cultural dimension, leading them to accept the red flags’ methodology. A questionnaire was addressed to a specific category of Greek auditors to identify the red flags having a specific impact on fraud prevention and detection, as well as the auditors' motivations. Among the red flags suggested, a significant proportion seem to be perceived as important, and the responses indicated openness and commitment to equality, feminism, and clear cooperation between stakeholders.

We document that firms with greater product similarity to their peers exhibit lower rates of financial fraud. We show that peer similarity is associated with better information environments, which is consistent with monitors’ enhanced ability to benchmark against other firms. The negative relation between product similarity and fraud remains after controlling for alternative mechanisms including incentive compensation structures, competition, and internal and external governance characteristics. Overall, our findings suggest that greater peer similarity increases the marginal cost of fraud, and therefore, ex ante disincentivizing managers from committing fraud.

Research summary: We examine the influence of CEOs' military background on financial misconduct using two distinctive datasets. First, we make use of accounting and auditing enforcement releases (AAER) issued by the U.S. Securities and Exchange Commission (SEC), which contain intentional and substantial cases of financial fraud. Second, we use a dataset of \"lucky grants,\" which provide a measure of the likelihood of grant dates of CEOs' stock options having been manipulated. Results for both datasets indicate that CEOs who served in the military are less inclined to be involved in fraudulent financial reporting and to backdate stock options. In addition, we find that these relationships are moderated by board oversight (CEO duality and independent directors in the board). Managerial summary: CEOs who formerly served in the U.S. military are prevalent among U.S. firms. The military puts strong emphasis on the obedience of its personnel. In this study, we test if time spent in the military leads individuals to be more obedient to rules and regulations in the years after they have left the military and become CEOs. Our findings strongly suggest that CEOs who served in the U.S. military are less likely to be involved in financial misconduct. We also find evidence that tougher board oversight strengthens this relationship. Our findings have implications for regulators, auditors, practitioners, and researchers who are interested in determinants of and mechanisms to prevent fraud and stock option backdating.

Purpose of the article: The purpose of this article is to provide a comprehensive analysis of the role of artificial intelligence (AI) in the banking sector, focusing on its applications, challenges, and implications. By synthesizing existing research and empirical studies, the article aims to inform researchers about the transformative potential and inherent challenges of AI-driven innovation in banking. Methodology/methods: Using a systematic review approach, the relevant literature on AI integration in banking was identified from electronic databases and leading corporate research departments, ensuring a synthesis of scholarly and industry perspectives. Scientific aim: With limited academic research on AI in banking, this study aims to shed light on its applications, challenges, and implications. Findings: The integration of AI in the banking sector has significantly transformed various operational areas, including customer interactions, risk management, compliance, and operational efficiency. AI applications, such as chatbots and smart virtual assistants, have enhanced customer service by offering personalized, 24/7 support, and have demonstrated significant cost and revenue benefits. AI-driven credit scoring and fraud detection have improved risk assessment and mitigation, enabling more precise and informed decision-making. However, AI adoption faces challenges such as high computational costs, data quality issues, the \"curse of recursion\" where models trained on AI-generated data degrade, and the need to balance trust in AI outputs with their reliability. Furthermore, regulatory considerations play a crucial role in AI integration. While the European Union's AI Act aims to ensure the ethical use of AI in finance, it also presents challenges related to compliance and potential over-regulation. Conclusions: In conclusion, the integration of AI in the banking sector has revolutionized customer service, risk management, compliance, and operational efficiency. However, the adoption of AI also raises concerns about data privacy, security, and the need for regulatory frameworks to ensure ethical use. As AI continues to evolve, it will be crucial for banks to balance technological innovation with responsible practices to maximize benefits and mitigate risks.

Machine learning offers empirical methods to sift through accounting datasets with a large number of variables and limited a priori knowledge about functional forms. In this study, we show that these methods help detect and interpret patterns present in ongoing accounting misstatements. We use a wide set of variables from accounting, capital markets, governance, and auditing datasets to detect material misstatements. A primary insight of our analysis is that accounting variables, while they do not detect misstatements well on their own, become important with suitable interactions with audit and market variables. We also analyze differences between misstatements and irregularities, compare algorithms, examine one-year- and two-year-ahead predictions and interpret groups at greater risk of misstatements.