Miklos A. Vasarhelyi

• PhD
• Professor at Rutgers Business School

SYNOPSIS Audit transaction anomalies can be viewed as outliers. Unsupervised learning methods of outlier detection do not require outcome labels and enable auditors to discover possible problems based on observed transaction patterns. This study develops a framework for using outlier detection methods in audit selection and evaluates the proposed f...

The integration of artificial intelligence into auditing opens up new pathways. By interpreting journal entries through the innovative lens of graphs, auditors are able to uncover complex accounting patterns and anomalies. This article illustrates how graph representation learning-based auditing can be applied in practice through two practical case...

Process mining is an efficient method that can analyze the full population of transactions using the event log of business processes. Conventional rule-based process mining techniques can detect anomalies; however, it tends to trigger a large number of false alarms. To improve the efficiency of anomaly detection using process mining, this study ado...

The press and pundits have extensively discussed the dangers of artificial general intelligence (AGI) and the various ethical and functional effects of current emerging technologies. This paper attempts to focus on AI as applied to accounting and auditing and its realities. It shows studies using machine learning and natural language processing, in...

The emergence of large language models (LLMs) presents significant opportunities in accounting, including optimizing current processes, extracting new information, and updating accounting measurements. However, factors such as skill gaps, perceived complexity of integration, and cost constraints have limited the implementation of LLMs in accounting...

Auditors traditionally use sampling techniques to examine general ledger (GL) data, which suffer from sampling risks. Hence, recent research proposes full-population testing techniques, such as suspicion scoring, which rely on auditors’ judgment to recognize possible risk factors and develop corresponding risk filters to identify abnormal transacti...

This study constructs a measure of audit quality that captures the effect of potential factors that are generally unobservable to people outside of the audit firm or client company. Using machine learning and a wide range of data describing audit firm characteristics, audit partners, and public companies in China, this paper constructs the “surpris...

Most anomaly detection models are developed by using expert system methods that mimic human experts. The process to capture the expertise honed by fraud examiners is complicated and practically challenging, often resulting in suboptimal models. This study proposes a clustering-based model that captures hidden characteristics of potentially fraudule...

Artificial intelligence exhibits the potential to transform auditing by extracting insights from large volumes of audit-relevant data. This article introduces federated learning, an emerging artificial intelligence learning setting. It outlines how to integrate federated learning into practical audit procedures to gather collective intelligence fro...

Recent studies and new standards suggest that auditors can use information from expanded external sources to verify their clients’ financial information. We propose advanced substantive analytical procedures with external nonfinancial measures derived from weather information to test whether it helps detect misstatements. Using computational simula...

This think piece looks at the traditional reporting for intangibles and concludes that the measuring and reporting of intangibles needs a structural rethinking to incorporate 21st-century technology involving new forward-looking information and methods to provide information that is consistent with current capabilities (e.g., apps, bots, multiple d...

Amidst the rapid growth of big data, the success of machine learning is critically tethered to the availability and quality of training data. A pertinent challenge faced by this symbiotic relationship is the issue of “low-resource data,” characterized by insufficient data volume, diversity, and representativeness, and exacerbated by class imbalance...

This commentary discusses how large language models like ChatGPT hold transformative potential in accounting, including education, research, and professional auditing. In the educational sphere, the advent of ubiquitous artificial intelligence (AI) tutors could potentially solve Bloom’s Two Sigma Problem, heralding a new era of personalized learnin...

Audit data analytics is gaining increasing attention from both audit researchers and practitioners. To provide accounting students with firsthand experience utilizing data analytics, this teaching case showcases the implementation of data analytic techniques to transactional-level data from real-world business practice. Specifically, this case demo...

Recent advances in technology have motivated and facilitated a revolution in the manufacturing domain, named “Industry 4.0.” Industry 4.0 significantly changes the manufacturing paradigm by linking the physical world with its virtual model, enabling communications among machines, enhancing collaborations across the value creation chain, and increas...

This study demonstrates a way of bringing an innovative data source, social media information, to the government accounting information systems to support accountability to stakeholders and managerial decision-making. Future accounting and auditing processes will heavily rely on multiple forms of exogenous data. As an example of the techniques that...

Aiming to assess the reliability of governmental accounting under an armchair-audit approach, we develop a framework to compare the financial reports submitted by municipalities to two different agencies: the Ministry of Finance and the respective Court of Accounts. We developed a framework using concepts of RPA in conjunction with OCR to download,...

This study conducts a pilot test analyzing reports from New York, New Jersey, and California and uses textual analytics to reengineer government performance audit reporting. It advocates a performance audit database that can facilitate easier access and extract relevant information from lengthy reports in a timely manner. The study presents a frame...

The International Standards on Auditing require auditors to collect reasonable assurance that financial statements are free of material misstatement. At the same time, a central objective of Continuous Assurance is the real-time assessment of digital accounting journal entries. Recently, driven by the advances in artificial intelligence, Deep Learn...

This paper presents a framework for proactive and intelligent continuous control monitoring (CCM) that helps management gain higher assurance over business processes and alleviate information overload. We adopt a design science approach towards systematically developing CCM artifacts, including operation and internal control violation display and m...

The current financial reporting systems are becoming obsolete due to the increasing sophistication of their users, the changing economic environment, and their inability to utilize current technology. This paper proposes an Extended Business Reporting App that will apply current technology, specifically app-based technology, to collect and integrat...

Artificial Intelligence (AI) and Machine Learning (ML) are gaining increasing attention regarding their potential applications in auditing. One major challenge of their adoption in auditing is the lack of explainability of their results. As AI/ML matures, so do techniques that can enhance the interpretability of AI, a.k.a., Explainable Artificial I...

Business transaction data includes numeric values of the transactions and the date/time when the transactions are recorded, and textual data such as descriptions. Understanding the textual information of business transactions is also important since this information captures the nature of transactions in a qualitative manner. This study proposes a...

Changes to the General Ledger (GL) represent a link between transactional business events from Journal Entries and prepared financial statements. Errors in these very large datasets can result in material misstatements or account misbalance. Unfortunately, a plethora of conditions renders traditional statistical and non-statistical sampling less ef...

We examine whether consumer-generated tweets about purchases (interest) and sentiment are useful in assessing the risk of misstated revenue in the planning stage of the audit, as reflected in improvements to analytical procedures, for firms in consumer-facing industries. We obtain consumer-generated tweeting activities from 2012 to 2017 for 76 comp...

Emerging technologies like data analytics and machine learning are impacting the accounting profession. In particular, significant changes are anticipated in audit and assurance procedures because of those impacts. One such potential change is audit sampling. As audit sampling only provides a small snapshot of the entire population, it starts to lo...

This learning strategy provides accounting faculty with a detailed course design and materials for a 3-credit, 14-week RPA course at the graduate level. This learning strategy is valuable in four respects. First, it leverages existing materials in the public domain and provides accounting faculty with a potential framework for using these materials...

Financial reporting and assurance in their current form are losing relevance to investors in firm valuations. New sources of data, especially exogenous or external data that are generated outside the organizations, have opened doors to new ways of business measurement and information validation. Examples of exogenous data include social media, onli...

This study responds to an increasing need for research on Robotic Process Automation (RPA) in external auditing, especially concerning auditors' roles in an RPA-enabled audit workflow. Since more than half of the audit tasks require certain levels of auditors' judgment and cannot be fully automated (Abdolmohammadi 1999), audit automation should inc...

Este estudo se insere no contexto das contratações no setor público e tem por objetivo apresentar o processo de desenvolvimento de um protótipo de Smart Contract a ser utilizado pelo Poder Executivo do Estado de Santa Catarina para gestão da lista básica de materiais. O estudo busca, incialmente, apresentar o processo de desenvolvimento do Smart Co...

We investigate and document the textual similarity of key audit matter (KAM) disclosures by using KAM items in auditor’s reports of Spanish companies in fiscal years 2017 and 2018. The main objective is to understand how similar KAMs are disclosed from one year to another. Following prior literature, we use the cosine similarity to measure the text...

Objetivo: esta pesquisa explora o papel que fatores sociais e políticas governamentais desempenham no desenvolvimento da pandemia de COVID-19. Enquadramento Teórico: o governo de diferentes regiões responde à pandemia com várias políticas e intervenções governamentais. Enquanto isso, fatores sociais que são resultados de longo prazo das políticas g...

Audit efficiency and effectiveness can be significantly affected by data aggregation during audit procedures. Previous studies highlight that an appropriate level of data aggregation is needed because a continuous auditing (CA) system often generates numerous alarms. To respond to this issue, this study proposes a CA system with a three-layer struc...

This paper advocates for a drastic transformation of government accountability and reporting. With the availability of Big Data and the advancement of technologies, the existing government reporting schema fails to meet the public's increasing demand for accountability. We discuss the need for the government to reform its reporting schema and presc...

Since data analytics enables data exploration and the uncovering of hidden relationships, in this study we use cluster analysis to gain more insight into governmental data and financial reports. This research initiative is performed using the Design Science Research (DSR) methodology, where we develop and apply an appropriate artifact. We apply our...

The purpose of this teaching note is to explain how Structured Query Language (SQL) queries can help auditors to independently retrieve properly formatted data as audit evidence or for further analyses. The note demonstrates data extraction using Microsoft (MS) Access, one of the simplest SQL compliant database software applications. We use a datas...

The Novel Coronavirus Disease, COVID-19, has been declared a worldwide pandemic by the World Health Organization (WHO) on March 11, 2020 (WHO 2020). Scientists in different fields have contributing to study the pandemic development and to provide support to government policies. However, the traditional measures of individual health, population heal...

Blockchain technology can benefit inter-organizational activities by improving data integrity, increasing transaction transparency, and decreasing transaction costs. In this paper, we discuss the strategic and economic value of this technology by applying it to the value-added tax (VAT) reporting system, focusing on blockchain’s characteristic trac...

Financial reporting has evolved over centuries in distinct stages. The first reports (Reporting 1.0) were the trial balances ensuring that debits equaled credits, using the terminology popularized by Pacioli. The next major innovation was formalized in the Great Depression, with Reporting 2.0 being the standardized and audited financial statements....

This study examines social media information within the context of social network theory by utilizing text mining techniques and machine learning algorithms to analyze the tweets and use the information as a proxy to measure the performance of municipal services. This study aims to provide the government with an additional performance measure to as...

Accounting firms are reporting the use of Artificial Intelligence (AI) in their auditing and advisory functions, citing benefits such as time savings, faster data analysis, increased levels of accuracy, more in-depth insight into business processes, and enhanced client service. AI, an emerging technology that aims to mimic the cognitive skills and...

SYNOPSIS Many accounting firms are starting to re-align their audit processes to incorporate technology and Audit Data Analytics (ADA), as the traditional procedures would seem to not be sufficiently effective and efficient to meet evolving market expectations (Byrnes et al. 2018; Forbes Insights 2017, 2018). This paper provides commentary on how d...

Managerial estimates are ubiquitous in accounting: most balance sheet and income statement items are based on estimates; some, such as the pension and employee stock options expenses, derive from multiple estimates. These estimates are affected by objective estimation errors as well as by managerial manipulation, thereby harming the reliability and...

The objective of this research is to build a forecasting model for the evolution of COVID-19 in the state to assist governmental decision-making. This study adopts the Continuous Intelligent Pandemic Monitoring (CIPM) methodology to evaluate the COVID-19 situation in the state of Santa Catarina, Brazil. By examining data from the state of Santa Cat...

The audit profession is facing a major transition toward a tech-savvy environment, i.e., extensively employing technologies such as data analytics and continuous auditing in daily work. During this transition, one of the biggest challenges is the lack of skilled and experienced auditors who are able to use technologies effectively and efficiently....

We examine private investors' funding preferences for cloud computing start-ups that provide services in various information technology (IT) areas. The funding preference is measured in funding size and frequency. Using data from CrunchBase, an unconventional dynamic database, we find significantly positive associations between the funding preferen...

The gradual but marked decline in the correspondence between aggregated accounting numbers and market valuations, such as stock returns, is a well-documented phenomenon in the research literature (Lev and Zarowin, 1999). Rapid advances in technology have paved the way for the collection of unprecedented volumes of data. Currently, the slow speed of...

Machine learning is a subset of artificial intelligence, and it is a computational method that learns patterns from large and complex data. The learning processes enable us to make predictions for future events. In the accounting and assurance profession, machine learning is gradually being applied to various tasks like reviewing source documents,...

Open government data (OGD) is attracting stakeholders from different backgrounds. The call for OGD has been especially pronounced in the last 6 or 7 years. OGD demand accelerated after the launch of the US OGD initiative portal in 2009, followed by the UK in 2010. Before that, the availability and accessibility of government data were limited to ce...

Robotic process automation (RPA) has been widely adopted in many industries, including the accounting industry, to automate well-defined and repetitive tasks; however, its application to auditing has lagged behind because of the unique nature of this industry. This study applies RPA in the auditing area. An RPA framework is proposed that frees audi...

A data ecosystem is a combination of relevant data and the technologies used to integrate information feeding a particular process or a set of functionalities. With the advent of substantially improved computing and storage capabilities, sophisticated algorithms, and easier access to exogenous data, the data ecosystem is facilitating increasingly a...

SYNOPSIS This introduction to Audit Data Analytics Research overviews the forum's five articles that showcase recent advances in audit data analytics technology and methodology. The articles are discussed through the prism of design science research that originates in engineering and computer science. In contrast with natural and social sciences th...

The emergence of enormous disparate data sources, available in a multitude of alternate formats, and on very different devices, is leading to a business process revolution. This paper argues for a new approach in which these technologies are used to replace outdated blanket government intervention programs. Highly targeted interventions for social...

There have been a number of requests of the full text of this manuscript. To my best knowledge, American Accounting Association provides free access to it. You may try the direct link as follows to access it: https://aaajournals.org/doi/pdf/10.2308/jeta-10640

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real‐life credit card da...

The advent of Robotic Process Automation (RPA) has the potential to disrupt the traditional audit model. With its capability to automate rules-based tasks that are repetitive and manual, RPA is expected to repurpose the role of the auditor by replacing perfunctory tasks and emphasizing higher order thinking skills that will eventually lead to enhan...

Purpose Prior studies suggest that non-timely 10-Q filings indicate higher potential risks than non-timely 10-K filings. Furthermore, larger audit firms tend to be more risk-averse and conservative about reporting. Inspired by these research streams, this paper aims to investigate the influence of non-timely 10-Q filings on audit fees and the impa...

This study examines whether firm use of XBRL extension elements increases the complexity of mandatory SEC filings. Using the ratio of extension elements to total elements in XBRL 10-K filings as the measure of XBRL complexity, we find that firms' XBRL filings are more complex when the firms are performing poorly, an effect that is more pronounced w...

There is an increasing recognition in the public audit profession that the emergence of big data as well as the growing use of business analytics by audit clients has brought new opportunities and challenges. That is, should more complex business analytics beyond the customary analytical procedures be used in the engagement and if so, where? Which...

A aproximação de áreas de negócio com o uso de novas tecnologias, economia em tempo real, transações com vários países e em vários continentes com diferentes garantias legais são necessárias. Essas garantias podem ser adquiridas por meio da Auditoria Contínua (CA). No entanto, para poder realizar a análise, os auditores precisam ter acesso e extrai...

The advances and continuous development of technology have been identified as significant influences on the accounting profession (AICPA, 1998). In the last twenty years, both academia and the accounting profession have been giving much attention to the demand and opportunity for audits to be performed automatically, continuously and in nearly real...

The evolution of MIS technology has affected traditional auditing and created a new set of audit issues. This paper describes the Continuous Process Auditing System (CPAS) developed at AT&T Bell Laboratories for the internal audit organization that is designed to deal with the problems of auditing large paperless real-time systems. The paper discus...