Thesis (Ph. D.)--University of Oregon, 2000. / Typescript. Includes vita and abstract. Includes bibliographical references (leaves 54-55). Also available for download via the World Wide Web; free to University of Oregon users.

This dissertation develops statistical and data mining based methods for insurance fraud detection. Insurance fraud is very costly and has become a world concern in recent years. Great efforts have been made to develop models to identify potentially fraudulent claims for special investigations. In a broader context, insurance fraud detection is a classification task. Both supervised learning methods (where a dependent variable is available for training the model) and unsupervised learning methods (where no prior information of dependent variable is available for use) can be potentially employed to solve this problem. First, an unsupervised method is developed to improve detection effectiveness. Unsupervised methods are especially pertinent to insurance fraud detection since the nature of insurance claims (i.e., fraud or not) is very costly to obtain, if it can be identified at all. In addition, available unsupervised methods are limited and some of them are computationally intensive and the comprehension of the results may be ambiguous. An empirical demonstration of the proposed method is conducted on a widely used large dataset where labels are known for the dependent variable. The proposed unsupervised method is also empirically evaluated against prevalent supervised methods as a form of external validation. This method can be used in other applications as well. Second, another set of learning methods is then developed based on the proposed unsupervised method to further improve performance. These methods are developed in the context of a special class of data mining methods, active learning. The performance of these methods is also empirically evaluated using insurance fraud datasets. Finally, a method is proposed to estimate the fraud rate (i.e., the percentage of fraudulent claims in the entire claims set). Since the true nature of insurance claims (and any level of fraud) is unknown in most cases, there has not been any consensus on the estimated fraud rate. The proposed estimation method is designed based on the proposed unsupervised method. Implemented using insurance fraud datasets with the known nature of claims (i.e., fraud or not), this estimation method yields accurate estimates which are superior to those generated by a benchmark naïve estimation method. / text

M. Tech. Policing / The purpose of this study was to solicit the views of the South African Police Service (SAPS) members, both at local police and the Commercial Crime Branch levels, as well as from the wider representatives from the community, regarding the weaknesses of the SAPS Commercial Crime Branch strategies towards responding to syndicate fraud activities.

Thesis (M.A.)--Naval Postgraduate School, 2004. / Title from title screen (viewed June 17, 2005). "MBA professional report"--Cover. "June 2004." Includes bibliographical references (p. 79-80). Also issued in paper format.

Thesis (M.S. in Operations Research)--Naval Postgraduate School, June 2002. / Thesis advisor(s): Samuel E. Buttrey, Lyn R. Whitaker. Includes bibliographical references (p. 103-105). Also available online.

Ph.D. (Computer Science) / Thanks to several advancements in communication technologies, the world today is a highly connected society promoting business transformations that highlight improved efficiency [1]. Unfortunately, systems developed for an increasingly connected world are also subject to increases in change, complexity and risk – the same connectedness that makes lives easier also signifies that any negative influences can be more difficult to handle and contain [2]. Multi-agent systems have been touted as ideal solutions to realising the required complexities across wide and varied problem domains that range from manufacturing [3] to eco-system management [4] to construction [5]. In an increasingly connected world, complex problems may require that various multi-agent systems work together in order to accomplish larger, overarching objectives. A fraud detection system, for example, could comprise a number of multi-agent systems, each designated to fulfil a very specific and important fraud detection task. The success of the fraud detection system will then depend on each of the various multi-agent systems’ abilities to achieve allocated goals and thus, contribute towards efforts to detect fraud accurately. Depending on factors that include objective and environment type, fraud detection tasks may entail working with numerous disparate systems [6] – it is possible that agent designs that are different from the rest of the fraud detection system must be implemented.Such inconsistency between multi-agent systems could potentially lead to conflicting goals, thereby jeopardising the resolution of the fraud detection system’s overall objectives. A further complication that may arise is the continuously changing financial services landscape – fraud detection systems must not only contend with the creativity of fraudsters, but should also be acutely aware of when day-to-day processes have changed due to recent innovations or technological advancements in the domain. Existing fraud detection methodologies may therefore need to be updated frequently in order to remain sufficiently informed of current developments. An agent-based fraud detection model was thus developed to assist anti-fraud professionals in the classification of day-to-day financial transactions. The proposed model comprises a number of multi-agent systems, each incorporated to add a particular aspect of the criminal justice process in investigating incidences of potential crime. By having agents emulate the various tasks that are involved in dealing with a crime, it is anticipated that the resulting fraud detection system will be able to achieve similar successes from applying the same procedure. In order to successfully develop the fraud detection model, an architecture for implementing a collaborative community of multi-agent subsystems for a dynamic environment was also developed. The architecture is intended to allow each multi-agent subsystem member to adapt to changes in the environment while ensuring that teamwork links are maintained amongst the different subsystems.

The role of internal auditors is evolving to enable them to provide stakeholders with assurance and to assist organisations to achieve objectives and remain competitive to ensure the future existence of their organisations. The research for this study was guided by the question of whether the Institute of Internal Auditors guidance pronouncements provide sufficient guidance in the light of expectations of both the institute and management (stakeholders) relating to the role of internal auditors in respect of fraud investigation. Literature reviewed on the role of internal auditors showed that there is limited guidance provided with regards to fraud investigation, knowledge and skills required by an internal auditor to perform fraud investigations. The research methodology used for this study consisted of a qualitative case study of the Nelson Mandela Metropolitan University committees, namely, Council, Senate and MANCO as well as a combination of deductive and inductive interpretative analysis methods. Semi-structured interviews were used to obtain data from participants who were randomly selected from Nelson Mandela Metropolitan University Council, Senate and MANCO committees. The interviews revolved around three themes, namely, the role of internal audit, the information expected from internal audits and the role that the internal audit plays with regard to fraud. The interviews were recorded by means of a digital voice recorder which were transcribed by a qualified transcriber. The collected data was then manually coded by making use of standardised coding methods to assist with the analyses of the data. After considering the participant responses in relation to the themes, it could be deduced that a greater awareness needed to be created regarding the role of the internal audit and the services which internal audits could provide to organisations and management structures. The results of the analyses revealed that an expectation gap existed with regard to the Institute of Internal Auditors, guidance pronouncements and stakeholder expectations of internal auditor roles with specific reference to fraud investigations. This study showed that the IIA’s guidance pronouncements do not provide sufficient and adequate guidance in respect of the knowledge, skills and competency capabilities in relation to fraud investigations.The results of the study further showed that the expected role of internal auditors in an organisation should include fraud investigations.

In recent years, the accounting profession has faced increased scrutiny because of scandals involving management fraud (e.g., Enron, WorldCom). In response, Statement on Auditing Standards (SAS) #99 has expanded auditors' responsibility for detecting fraud, requiring auditors to gather significantly more information in their assessment of fraud. In addition, the Public Company Accounting Oversight Board (PCAOB) will focus on fraud detection through their inspections of registered accounting firms. In light of the increased emphasis on auditors' responsibility for detecting fraud, public accounting firms face the challenge of improving their fraud detection process, including their assessment of management fraud risk. Decision aids are one way for auditors to improve their assessment of management fraud risk. In fact, several studies from the decision aid literature suggest that aids are useful tools for a variety of tasks, including fraud risk assessment. At the same time, another stream of the decision aid reliance literature, which looks at people's willingness to rely on decision aids, suggests that individuals tend to be reluctant to accept the output given by an aid. Thus, the primary focus of this paper is on uncovering factors that would encourage one to voluntarily use and rely upon a decision aid. Toward that end, 132 senior-level auditors participated in an experiment that examined how several factors (confidence, perceived usefulness, client size, and conformity pressure) affect decision aid usage and reliance. The results show that perceived usefulness and decision aid reliance are significantly related. Further, the results suggest that perceived usefulness affects reliance more than variables examined in prior studies (e.g., confidence). Finally, the results suggest that decision aid usage mediates the relationship between perceived usefulness and reliance. The results of the current study have important implications for research in both the information systems and decision aid reliance areas. First, the study shows that perceived usefulness, a significant construct from the technology acceptance model (TAM) literature, is also a significant factor in determining decision aid usage and reliance. Second, the study further delineates how certain factors affect decision aid reliance.

The analysis of bank account statements to establish evidence of illicit financial activity is an established financial investigation methodology in countries such as the United States and the United Kingdom, but it is still in its infancy in South Africa. This is further highlighted by virtue of the fact that no uniform analysis methodology is used in South Africa for the analysis of bank account statements. The purpose of the research was to explore the role of such analysis, and the current practises in South Africa and New Jersey in the United States. This was to determine a practical model for the analysis of bank account statements in the South African context. Empirical research led to a proposed process model for such analysis, which was synthesised from current practises in South Africa and New Jersey in the United States. This model is proposed as the basis for the development of a uniform analysis methodology for the examination of bank account statements. / Die analise van bankrekeningstate om bewys van onwettige finasiële aktiwiteite te bepaal is 'n vasgestelde finansiële ondersoek metode in lande soos die Verenigde State en die Verenigde Koningkryk, maar in Suid-Afrika is dit steeds in die begin stadium. Dit is verder beklemtoon deur die feit dat daar geen eenvormige analise metode in Suid-Afrika in gebruik is vir die analise van bankrekeningstate. Die doel van die navorsing was om die rol van hierdie tipe analise, en die huidige praktyk in Suid-Afrika en New Jersey in die Verenigde State te bepaal. Dit was om 'n praktiese model vir die analise van bankrekeningstate in Suid-Afrika te bepaal. Empiriese navorsing het gelui tot 'n voorgestelde proses model vir hierdie tipe analise, wat 'n samesmelting van die huidige Suid-Afrikaanse en New Jersey in die Verenigde State praktyk is. Hierdie model word voorgestel as die beginpunt vir die ontwikkeling van 'n eenvormige analise metode vir die ondersoek van bankrekening state. / Criminology / M.Tech. (Forensic Investigation)

The analysis of bank account statements to establish evidence of illicit financial activity is an established financial investigation methodology in countries such as the United States and the United Kingdom, but it is still in its infancy in South Africa. This is further highlighted by virtue of the fact that no uniform analysis methodology is used in South Africa for the analysis of bank account statements. The purpose of the research was to explore the role of such analysis, and the current practises in South Africa and New Jersey in the United States. This was to determine a practical model for the analysis of bank account statements in the South African context. Empirical research led to a proposed process model for such analysis, which was synthesised from current practises in South Africa and New Jersey in the United States. This model is proposed as the basis for the development of a uniform analysis methodology for the examination of bank account statements. / Die analise van bankrekeningstate om bewys van onwettige finasiële aktiwiteite te bepaal is 'n vasgestelde finansiële ondersoek metode in lande soos die Verenigde State en die Verenigde Koningkryk, maar in Suid-Afrika is dit steeds in die begin stadium. Dit is verder beklemtoon deur die feit dat daar geen eenvormige analise metode in Suid-Afrika in gebruik is vir die analise van bankrekeningstate. Die doel van die navorsing was om die rol van hierdie tipe analise, en die huidige praktyk in Suid-Afrika en New Jersey in die Verenigde State te bepaal. Dit was om 'n praktiese model vir die analise van bankrekeningstate in Suid-Afrika te bepaal. Empiriese navorsing het gelui tot 'n voorgestelde proses model vir hierdie tipe analise, wat 'n samesmelting van die huidige Suid-Afrikaanse en New Jersey in die Verenigde State praktyk is. Hierdie model word voorgestel as die beginpunt vir die ontwikkeling van 'n eenvormige analise metode vir die ondersoek van bankrekening state. / Criminology and Security Science / M.Tech. (Forensic Investigation)