Search results

This paper tests whether Bayesian A/B testing yields better decisions that traditional Neyman-Pearson hypothesis testing. It proposes a model and tests it using a large, multiyear Google Analytics (GA) dataset.

This paper is an empirical study. Competing A/B testing models were used to analyze a large, multiyear dataset of GA dataset for a firm that relies entirely on their website and online transactions for customer engagement and sales.

Bayesian A/B tests of the data not only yielded a clear delineation of the timing and impact of the intellectual property fraud, but calculated the loss of sales dollars, traffic and time on the firm’s website, with precise confidence limits. Frequentist A/B testing identified fraud in bounce rate at 5% significance, and bounces at 10% significance, but was unable to ascertain fraud at the standard significance cutoffs for scientific studies.

None within the scope of the research plan.

Bayesian A/B tests of the data not only yielded a clear delineation of the timing and impact of the IP fraud, but calculated the loss of sales dollars, traffic and time on the firm’s website, with precise confidence limits.

Bayesian A/B testing can derive economically meaningful statistics, whereas frequentist A/B testing only provide p-value’s whose meaning may be hard to grasp, and where misuse is widespread and has been a major topic in metascience. While misuse of p-values in scholarly articles may simply be grist for academic debate, the uncertainty surrounding the meaning of p-values in business analytics actually can cost firms money.

There is very little empirical research in e-commerce that uses Bayesian A/B testing. Almost all corporate testing is done via frequentist Neyman-Pearson methods.

Are financially illiterate individuals all the same? This study aims to answer this question. Specifically, the authors investigate whether people answering incorrectly and “do not know” to the big five questions about financial knowledge (FK), all identified by previous literature as financially illiterate, are two sides of the same coin, or rather individuals with different socio-economic and demographic characteristics, and whether this leads to different levels of risk of falling victim to financial fraud.

Using a large and representative sample of Italian adults, the authors run both ordered probit and probit regressions to test the determinants of financially illiterate individuals, distinguishing between those answering FK questions incorrectly and those answering “do not know”. The authors also measure the probability of falling victim to financial fraud for the two groups. To check the robustness of our results, the authors run a multinomial regression, a structural equation model and an instrumental variable regression model.

The authors demonstrate that the socio-demographic and socio-economic characteristics of individuals selecting incorrect responses to FK questions are different from those of individuals selecting the “do not know” option. Moreover, the results show that the former are more likely to be victims of financial frauds.

The “one-size-fits-all” approach is not suitable for financial education. It is important to consider socio-demographic and socio-economic characteristics of individuals in order to identify specific targets of education programmes aiming to reduce insecurity and excessive self-confidence as well as to increase objective FK. The study’s findings also identify vulnerable groups to which financial fraud prevention schemes should be targeted.

To date, financial illiteracy has been measured as the sum of incorrect and “do not know” responses given to FK questions. This approach does not allow to observe the socio-demographic and socio-economic differences between people choosing the “do not know” option and those answering incorrectly. The paper aims to overcome this limit by investigating the socio-demographic and socio-economic characteristics of individuals selecting “do not know” and incorrect responses, respectively. The authors also investigate whether the two groups have different probabilities of being victims of financial fraud.

The unhealthy drive for deposit in the banking sector has pushed many banks into unethical practices, thereby resulting in high-level corruption cases in the banking sector. The purpose of this study is to investigate the short- and long-run linkages between bank net interest income and deposit liabilities interacted with corruption, to establish the influence of corruption in deposit mobilisation drive of banks in Nigeria. Also, the study analysed the causal relationship between selected bank variables and fraud.

The study used quarterly data on selected variables from 1Q 1993 to 4Q 2017 sourced from Nigerian Deposit Insurance Corporation (NDIC) annual reports and Central Bank of Nigeria (CBN) Statistical Bulletin of various issues. Deposit Money Bank various deposit liabilities are interacted with a corruption index and used as the independent variables, while bank earnings serve as the dependent variable. Error Correction Model (ECM) and Engel Granger approach to co-integration technique were used to analyse the data.

The findings reveal that various bank deposit liabilities interacted with corruption index has a negative effect on bank profitability in the long run, though only corrupt fixed deposit is statistically significant at the 5 per cent significance level. Bank total asset, total loan and advances and fraud have a significant effect on bank profitability at 1 and 10 per cent significance level. The findings also reveal that banks profit from corrupt fixed deposit and demand deposit in the short run.

Text

The literature is awash with bank lending corruption and various institutional factors such as competition among banks, credit bureau and information sharing about borrowers, bank supervisory policies, loan loss provisioning, bank ownership structure and regulatory environment and anti-corruption measures. The aspect of deposit mobilisation and corruption has not been well researched in literature; this study, therefore, fills the gap in the literature by examining the extent deposit money banks contributed to corruption in Nigeria through their cutthroat deposit mobilisation drive.

This study reviews and discusses the accounting literature that analyzes the role of auditors and enforcers in the context of fraud.

This literature review includes both qualitative and quantitative studies, based on the idea that the findings from different research paradigms can shed light on the complex interactions between different financial reporting controls. The authors use a mixed-methods research synthesis and select 64 accounting journal articles to analyze the main proxies for fraud, the stages of the fraud process under investigation and the roles played by auditors and enforcers.

The study highlights heterogeneity with respect to the terms and concepts used to capture the fraud phenomenon, a fragmentation in terms of the measures used in quantitative studies and a low level of detail in the fraud analysis. The review also shows a limited number of case studies and a lack of focus on the interaction and interplay between enforcers and auditors.

This study outlines directions for future accounting research on fraud.

The analysis underscores the need for the academic community, policymakers and practitioners to work together to prevent the destructive economic and social consequences of fraud in an increasingly complex and interconnected environment.

This study differs from previous literature reviews that focus on a single monitoring mechanism or deal with fraud in a broadly manner by discussing how the accounting literature addresses the roles and the complex interplay between enforcers and auditors in the context of accounting fraud.

The purpose of this paper is to estimate tax evasion and its impact on progressivity, redistribution and the measurement of inequality, using microdata from the Spanish income tax for 2001-2004.

The approach follows Feldman and Slemrod (2007) by exploiting the relation of charitable donations with the composition of income but introduces two methodological innovations, which could be useful for further studies: correction for sample selection with a Heckman two-step setting and the calculation of different evasion rates for top incomes with an interaction term.

Evasion in capital incomes was significant throughout these years. Financial incomes were reported at around 50-70 per cent of their real value, with the lowest estimates corresponding to the top decile. Revenues from fixed capital display similarly low compliance rates for the top 10 per cent. Tax evasion in self-employment incomes (direct assessment) is estimated at 20 per cent for 2001. Mostly because of a composition effect, this means that fraud was higher at the top of the income distribution, thus having a regressive impact. Inequality statistics and top income concentration estimates should, therefore, be revised upwards.

This is the first paper to estimate the distributive impacts of tax evasion in Spain, and one of very few internationally.

This paper aims to explain the fundraising and valuation processes of startups and discuss the conflicts of interest between entrepreneurs, venture capital (VC) firms and stakeholders in the context of startup corporate governance. Further, this paper uses the examples of WeWork and Zenefits to explain how a failure of stakeholders to demand an external audit from an independent accounting firm in early stages of funding led to an opportunity for fraud.

The methodology used is a literature review and analysis of startup valuation combined with the Fraud Triangle Theory. This paper also provides a discussion of WeWork and Zenefits, both highly visible examples of startup fraud, and explores an increased role for independent external auditors in fraud risk mitigation on behalf of stakeholders prior to an initial public offering (IPO).

This paper documents a number of fraud risks posed by the “fake it till you make it” ethos and investor behavior and pricing in the world of entrepreneurial finance and VC, which could be mitigated by a greater awareness of startup stakeholders of the value of an external audit performed by an independent accounting firm prior to an IPO.

An implication of this paper is that regulators should consider greater oversight of the startup financing process and potentially take steps to facilitate greater independence of participants in the IPO process.

Given the potential conflicts of interest between VC firms, investment banks and startup founders, the investors at the time of an IPO may be exposed to the risk that the shares of the IPO firms are overvalued at offering.

This study demonstrates how startup practices can be extended to the Fraud Triangle and issue a call to action for the accounting profession to take a greater role in protecting the public from startup fraud. This study then offers recommendations for regulators and standards entities.

There are few academic papers in the financial crime literature that link the valuation and culture of startup firms with fraud risk. This study provides a concise explanation of the process of valuation for startups and highlights the considerations for stakeholders in assessing fraud risk. In addition, this study documents an emerging role for auditors as stewards of proper valuation for pre-IPO firms.

The purpose of this paper is to evaluate the possibility of rating the credit worthiness of a firm’s quarterly financial report using a dynamic anomaly detection method.

The study uses a data set containing financial statements from Quarter 1 – 2001 to Quarter 4 – 2016 of 937 Vietnamese listed firms. In sum, 24 fundamental financial indices are chosen as control variables. The study employs the Mahalanobis distance to measure the proximity of each data point from the centroid of the distribution to point out the extent of the anomaly.

The finding shows that the model is capable of ranking quarterly financial reports in terms of credit worthiness. The execution of the model on all observations also revealed that most financial statements of Vietnamese listed firms are trustworthy, while almost a quarter of them are highly anomalous and questionable.

The study faces several limitations, including the availability of genuine accounting data from stock exchanges, the strong assumptions of a simple statistical distribution, the restricted timeframe of financial data and the sensitivity of the thresholds for anomaly levels.

The study opens an avenue for ordinary users of financial information to process the data and question the validity of the numbers presented by listed firms. Furthermore, if fraud information is available, similar research can be conducted to examine the tendency for companies with anomalous financial reports to commit fraud.

This is the first paper of its kind that attempts to build an anomaly detection model for Vietnamese listed companies.

The purpose of this paper is to analyze the effects of financial restatements (FRs) on the likelihood of the top management team (TMT) dismissal. It investigates the effects of types of FRs [corrective note and reissuance of financial statement (RFS)], of FR severity and of FR related to international financial reporting standards (IFRSs) easy or difficult-to-estimate.

The authors hand-collect: data about 96 FRs from the Italian public oversight board documents; chief executive officer (CEO) name, chairman name, year of the financial statement under investigation, total assets and operating income, from their financial statement. The authors use multivariate regression to test the effects of FRs on the probability of TMT dismissal.

The authors find that the RFS leads to a higher likelihood of chairman dismissal. A greater magnitude of misrepresentation on income statements, and FRs, which decrease net income, increase the likelihood of CEO dismissal. Difficult-to-estimate IFRSs increases the likelihood of CEO dismissal.

FRs are significant determinants of the CEO/chairman dismissal. The authors show that FRs directly involving shareholders (RFS) have negative consequences on the chairman of the board of directors, while the CEO is more affected by FRs that involve technical factors (FR severity or financial statement associated with difficult-to-estimate IFRSs).

This study aims to fill the gap in previous research that focuses on the superficial aspects of equity crowdfunding (ECF) campaigns and financial practices by examining financial literacy aspects, such as due diligence and valuation, in terms of factors that influence Japanese individual investors' investments in ECF.

The status of information disclosure in ECF campaigns is checked. In addition, the feasibility of the initial due diligence and valuation using this information is verified. Specifically, the lack of financial literacy hypothesis is developed and (1) expected market capitalization in the final fiscal year of the business plan and (2) expected returns on investment (IRR: internal rate of return) are estimated.

ECF campaigns in Japan disclose information equivalent to that obtained by professional venture capitalists. Analysis of the disclosed business plan allows for initial due diligence and valuation. By contrast, due diligence reveals that some projects are unlikely to be listed even if their business plans are met, and others have low IRRs. In addition, a stock acquisition rights project, in which even professional investors are unable to calculate IRRs, is completed at the same rate as a common stock project; this suggests that individual investors lack financial literacy.

Analyzing ECF from financial literacy aspects, such as due diligence and valuation, is unique. Such aspects are essential for private equity investments but have not been addressed in previous studies.

The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential money laundering. The model is applied to a large data set from Norway’s largest bank, DNB.

A supervised machine learning model is trained by using three types of historic data: “normal” legal transactions; those flagged as suspicious by the bank’s internal alert system; and potential money laundering cases reported to the authorities. The model is trained to predict the probability that a new transaction should be reported, using information such as background information about the sender/receiver, their earlier behaviour and their transaction history.

The paper demonstrates that the common approach of not using non-reported alerts (i.e. transactions that are investigated but not reported) in the training of the model can lead to sub-optimal results. The same applies to the use of normal (un-investigated) transactions. Our developed method outperforms the bank’s current approach in terms of a fair measure of performance.

This research study is one of very few published anti-money laundering (AML) models for suspicious transactions that have been applied to a realistically sized data set. The paper also presents a new performance measure specifically tailored to compare the proposed method to the bank’s existing AML system.