MetaFraud: A Meta-Learning Framework for Detecting Financial Fraud

Abstract

Financial fraud can have serious ramifications for the long-term sustainability of an organization, as well as adverse effects on its employees and investors, and on the economy as a whole. Several of the largest bankruptcies in U.S. history involved firms that engaged in major fraud. Accordingly, there has been considerable emphasis on the development of automated approaches for detecting financial fraud. However, most methods have yielded performance results that are less than ideal. In consequence, financial fraud detection continues as an important challenge for business intelligence technologies. In light of the need for more robust identification methods, we use a design science approach to develop MetaFraud, a novel meta-learning framework for enhanced financial fraud detection. To evaluate the proposed framework, a series of experiments are conducted on a test bed encompassing thousands of legitimate and fraudulent firms. The results reveal that each component of the framework significantly contributes to its overall effectiveness. Additional experiments demonstrate the effectiveness of the meta-learning framework over state-of-the-art financial fraud detection methods. Moreover, the MetaFraud framework generates confidence scores associated with each prediction that can facilitate unprecedented financial fraud detection performance and serve as a useful decision-making aid. The results have important implications for several stakeholder groups, including compliance officers, investors, audit firms, and regulators.

Generalized optimal wavelet decomposing algorithm for big financial data

“…Chen et al (2012) highlight five big data applications for business intelligence based on the new generation of data analytics savvy. Hu et al (2012) use network analytics for risk management and Abbasi et al (2012) employ a meta-learning framework for detecting financial fraud. Klassen and Vereecke (2012) discuss social issues in supply chain and Wuttke et al (2013) summarize some typical methods of financial supply chain management.…”

Who Can We Trust: A New Approach for Fraudulent Rater Detection in Reputation Systems

“…Methods for fraud detection have been widely studied. One research stream has designed detection mechanisms to analyze and cope with various fraud types, such as financial fraud (Abbasi, Albrecht, Vance, & Hansen, 2012) and management fraud (Cecchini, Aytug, Koehler, & Pathak, 2010). The methods proposed in this line of research usually require designing a model with a set of cues specific to that particular fraud.…”

Towards an understanding of the role of business intelligence systems in organisational knowing

“…Several studies have reported that BI systems facilitate organisational decision-making by identifying opportunities and problems (Truxillo et al, 2012) and by detecting trends or patterns in customer behaviours (Chau & Xu, 2012), operations (VanDiver et al, 2009 and business processes (Elbashir & Williams, 2007). In a recent special issue on BI in MIS Quarterly, many of the articles see BI systems as a technology that focuses on extracting intelligence or new insights from implementing BI methods and techniques (Abbasi et al, 2012;Hu et al, 2012;Lau et al, 2012;Park et al, 2012;Sahoo et al, 2012). The process of extracting insights and using these to drive action is directly linked to processes of organisational knowing (Choo, 1998).…”