Financial fraud detection and big data analytics – implications on auditors’ use of fraud brainstorming session

Tang, Jiali; Karim, Khondkar E.

doi:10.1108/maj-01-2018-1767

Cited by 75 publications

(61 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Analyzing this structured data further enables companies such as banks to detect fraudulent activities. Tang and Karim (2019) reveal that dig data analytics help strengthen results, identify fraud indicators, and document current issues in banks. This fraud detection theme has also been recognized by researchers in the context of big data and listed in the content analysis table.…”

Section: Research Themesmentioning

confidence: 99%

Big Data Applications the Banking Sector: A Bibliometric Analysis Approach

et al. 2021

View full text Add to dashboard Cite

This study aims to review the existing literature on big data applications in banking using a bibliometric analysis approach. This approach describes citation rates, research outputs, and their implementations, along with current streams in the field and future research agenda. The articles were selected from 2012 to 2020 and sorted by the citation rate in results and analysis. We have discovered 60 papers related to big data in banking, although the applications of big data in the banking sector are growing rapidly, the number of research output in this field is limited. Several themes are extracted from the studies that are reviewed, analyzed, and presented in this report. This review covered the themes that include investment, profit, competition, credit risk analysis, banking crime, and fintech. This report also signifies the importance, use of big data, and its function in the banking and financial sector. This study has also discussed the future research scope in the banking industry’s big data analytics.

show abstract

Section: Research Themesmentioning

confidence: 99%

Big Data Applications the Banking Sector: A Bibliometric Analysis Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Many studies documented the benefit of using a combination of structured and unstructured data in audit evidence (Janvrin & Weidenmier Watson, 2017;Astami et al, 2017). Tang and Karim (2019) found that an auditor's use of unstructured data is still limited and thus recommended upgrading the practitioners' skills to manage the data variety, velocity, volume, veracity, and value. Because the benefits of big data use in the auditing process could vary based on the precise time used, the use of big data interpretation, as having been documented, provides better advantages if used after evaluating the traditional audit evidence (Rose et al, 2017).…”

Section: Emerging Technologies In Auditing and Assurancementioning

confidence: 99%

Audit and tax in the context of emerging technologies: A retrospective analysis, current trends, and future opportunities

Atayah¹,

Alshater²

2021

IJDAR

View full text Add to dashboard Cite

This study aims to review the existing literature on audit and tax in the context of emerging technologies, besides providing future research agenda. A meta literature approach by combining bibliometric and content analysis was adopted to analyze 154 relevant English articles published in Scopus indexed journals, published over the last 35 years. Using RStudio, VOSviewer, and Microsoft Excel. Quantitative findings reveal that the USA is the top contributor and the most cited in the world. Brigham Young University, on the institutional level, is the most relevant affiliation. Concerning publication number, the Journal of Emerging Technologies in Accounting is the most relevant source. At the same time, the most cited source is the Decision Sciences journal. While the most prolific author is Miklos Vasarhelyi. Moreover, the emerging technologies, including big data, blockchain, and artificial intelligence, have significantly drawn accounting scholars interest from 2015 and thereafter. From the perspective of qualitative findings, the main focus shows that employing advanced technologies offers promising opportunities to mitigate the risk of tax evasion and enhance the auditors' efficiency. The content analysis reports two mainstreams tax and audit; each one is classified into three sub-streams, big data, artificial intelligence, and blockchain. This study contributes to present a clear and coherent understanding of the relevant exact literature and propose future research. However, the study review confines only on audit and tax fields, relying on the Scopus database.

show abstract

“…According to the existing relevant researches [22,23], this paper selects the appropriate financial indicators from nine categories of profitability, operating capacity, development capacity, per share index, ratio structure, solvency, risk level, disclosure of financial indicators, and cash flow analysis as the features of financial fraud identification.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Intelligent Prediction Mathematical Model of Industrial Financial Fraud Based on Data Mining

Geng

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The essence of enterprise financial modeling is to use mathematical models to classify and sort out all kinds of enterprise information according to the main line of value creation and on this basis to complete the analysis, prediction, and value evaluation of enterprise financial situation. A reasonable financial model is also an effective means to reduce financial fraud. In this paper, a financial fraud identification model is constructed based on empirical data. In the process of model construction, the primary feature set is selected according to the financial fraud motivation theory, and then, the original feature set is obtained by Mann–Whitney test on the primary feature set, and the final fraud identification feature set is selected from the original feature set by using Relief and Boruta algorithms. Finally, based on the final fraud identification feature set, the data algorithms such as decision tree, logistic regression, support vector machine, and random forest are used to identify financial fraud. The experimental results show that the combination of financial fraud identification features constructed by the Relief algorithm and random forest model has the best recognition effect. The evaluation indexes of the G mean value and the F value were 75.86% and 78.33%, respectively.

show abstract

Financial fraud detection and big data analytics – implications on auditors’ use of fraud brainstorming session

Cited by 75 publications

References 64 publications

Big Data Applications the Banking Sector: A Bibliometric Analysis Approach

Big Data Applications the Banking Sector: A Bibliometric Analysis Approach

Audit and tax in the context of emerging technologies: A retrospective analysis, current trends, and future opportunities

Intelligent Prediction Mathematical Model of Industrial Financial Fraud Based on Data Mining

Contact Info

Product

Resources

About