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

Abstract

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.

On verifying the authenticity of e-commercial crawling data by a semi-crosschecking method

“…Through manual investigations on the semantics of data features on C2C e-commercial websites (Yoo et al, 2016), we come up with some dependencies between attributes of the data. As the attributes extracted from an URL have relationships in their values if we modify an attribute, the new value can break its dependencies with the other attributes and hence the data will be detected as anomalies (Gupta and Gill, 2012). Some typical dependencies for fraud detection on C2C e-commercial websites are discussed in the following sections.…”

Finding Needles in a Haystack: Using Data Analytics to Improve Fraud Prediction

“…-6 -Early research within this stream concludes that artificial neural networks perform well relative to discriminant analysis and logistic regressions (e.g., Green and Choi 1997;Fanning and Cogger 1998;Lin, Hwang, and Becker 2003). More recent research in this stream examines additional classification algorithms, such as support vector machines, decision trees, and adaptive learning methods (e.g., Cecchini, Koehler, Aytug, and Pathak 2010;Perols 2011;Abbasi, Albrecht, Vance, and Hansen 2012;Gupta and Gill 2012;Whiting et al 2012) and text mining methods (e.g., Glancy and Yadav 2011;Humpherys, Moffitt, Burns, Burgoon, and Felix 2011;Goel and Gangolly 2012;Larcker and Zakolyukina 2012). We follow recent fraud data analytics research (e.g., Cecchini et al 2010) and findings in Perols (2011) and implement all prediction models using support vector machines.…”