A Data Mining Framework for Prevention and Detection of Financial Statement Fraud

Gupta, R.; Gill, Nasib Singh

doi:10.5120/7789-0889

Cited by 20 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will see that when we move into the field of fraud and remediation investigation, the use of behavioral science becomes even more interesting (Ramamoorti, 2008). To reduce fraud in financial statements, which include detection and prevention, Gupta and Gill (2012) propose the use of predictive and exploration techniques of data used in the literature. Jacquinot et al (2011) believe that in a business, the top leaders must be role models.…”

Section: The Fraud Costsmentioning

confidence: 99%

Fraud and Governance: A Review June 2020

Sayumwe¹

2020

BMER

View full text Add to dashboard Cite

show abstract

Section: The Fraud Costsmentioning

confidence: 99%

Fraud and Governance: A Review June 2020

Sayumwe¹

2020

BMER

View full text Add to dashboard Cite

show abstract

“…Chow and Rice (1992) argue that high debt levels increase the likelihood of fraudulent financial reporting. Gupta and Gill (2012) had classified organizations as fraudulent or not fraudulent by using indexes or financial ratios related to profitability, liquidity and operational efficiency. Dyreng et al (2010) shows that companies in specific business sectors (oil and gas industry, mining, insurance and real estate) can sustain an effective tax using such features like company size, tax havens or high levels of tangible and intangible assets.…”

Section: Literature Review On Taxpayers' Segmentation and Related Issuesmentioning

confidence: 99%

Theoretical Approach to Taxpayers’ Segmentation

Stankevičius

Kundeliene

2017

Proceedings of 5th International Scientific Conference Contemporary Issues in Business, Management and Education ‘2017

View full text Add to dashboard Cite

Current taxpayers’ segmentation is relatively limited and static. The existing segmentation problem, which is related to the taxpayers ‘behaviour, requires modern segmentation-analysis methods and models, which would evaluate the change of economic and psychographic taxpayers‘indicators. Purpose of the study: to provide conceptual taxpayers’ segmentation model, which allows to classify and analyse them according to the taxpayers’ behaviour and known legal facts. Research is based on analytical approach, there were invoked a systemic, logical and comparative analysis of scientific literature. Findings: the knowledge about the specific behaviour of the taxpayers‘ segment groups (tax compliance/ enforced tax obligations) would enable us to determine the main impacting factors. Better comprehension of the taxpayers‘ and their executives (decision-makers) behaviour would allow to enhance administrative institutions' abilities in analytics and to determine the unknown yet connections and phenomenons between separate taxpayers in the context of effectual law basis. Clearer taxpayers‘ identification by segment groups and behaviour risk factors, which are specific to separate groups, will enable faster determination of outliers as well as newly forming potential risks. Dynamic changes between separate groups or in them will form preconditions for timely implemention of taxpayers‘ monitoring and control tools for reaching a positive change in the behaviour of taxpayers.

show abstract

“…Recently, Gupta & Gill [16] examined the efficacy of three data mining techniques namely CART, Naïve Bayesian Classifier and Genetic Programming on detecting fraudulent financial statements. CART manages to classify 96% of the cases and outperforms other two methods in terms of sensitivity and specificity.…”

Section: Related Workmentioning

confidence: 99%

A Solution for Preventing Fraudulent Financial Reporting using Descriptive Data Mining Techniques

Gupta¹,

Gill²

2012

IJCA

Self Cite

View full text Add to dashboard Cite

In the present age of scams, financial statement fraud represents enormous cost to our economy. The deliberate misstatement of numbers in the accounting books with the help of well planned scheme by an intelligent squad of knowledgeable perpetrators in order to deceive the capital market participants is termed as financial statement fraud. In order to reduce fraud risk which comprehends both detection and prevention of financial statement fraud, this paper implements descriptive data mining techniques such as Association rules and clustering as opposed to predictive data mining techniques used in the literature. Each of these techniques is applied on dataset obtained from financial statements namely balance sheet, income statement and cash flow statement of 114 companies.

show abstract

A Data Mining Framework for Prevention and Detection of Financial Statement Fraud

Cited by 20 publications

References 31 publications

Fraud and Governance: A Review June 2020

Fraud and Governance: A Review June 2020

Theoretical Approach to Taxpayers’ Segmentation

A Solution for Preventing Fraudulent Financial Reporting using Descriptive Data Mining Techniques

Contact Info

Product

Resources

About