Dissertations / Theses on the topic 'Fraudulent detection'

With the increased global use of online media platforms, there are more opportunities than ever to misuse those platforms or perpetrate fraud. One such fraud is within the music industry, where perpetrators create automated programs, streaming songs to generate revenue or increase popularity of an artist. With growing annual revenue of the digital music industry, there are significant financial incentives for perpetrators with fraud in mind. The focus of the study is extracting user behavioral patterns and utilising them to train and compare multiple supervised classification method to detect fraud.  The machine learning algorithms examined are Logistic Regression, Support Vector Machines, Random Forest and Artificial Neural Networks. The study compares performance of these algorithms trained on imbalanced datasets carrying different fractions of fraud. The trained models are evaluated using the Precision Recall Area Under the Curve (PR AUC) and a F1-score. Results show that the algorithms achieve similar performance when trained on balanced and imbalanced datasets. It also shows that Random Forest outperforms the other methods for all datasets tested in this experiment.
Med den ökande användningen av strömmande media ökar också möjligheterna till missbruk av dessa platformar samt bedrägeri. Ett typiskt fall av bedrägeri är att använda automatiserade program för att strömma media, och därigenom generera intäkter samt att öka en artist popularitet. Med den växande ekonomin kring strömmande media växer också incitamentet till bedrägeriförsök. Denna studies fokus är att finna användarmönster och använda denna kunskap för att träna modeller som kan upptäcka bedrägeriförsök. The maskininlärningsalgoritmer som undersökts är Logistic Regression, Support Vector Machines, Random Forest och Artificiella Neurala Nätverk. Denna studie jämför effektiviteten och precisionen av dessa algoritmer, som tränats på obalanserad data som innehåller olika procentandelar av bedrägeriförsök. Modellerna som genererats av de olika algoritmerna har sedan utvärderas med hjälp av Precision Recall Area Under the Curve (PR AUC) och F1-score. Resultaten av studien visar på liknande prestanda mellan modellerna som genererats av de utvärderade algoritmerna. Detta gäller både när de tränats på balanserad såväl som obalanserad data. Resultaten visar också att Random Forestbaserade modeller genererar bättre resultat för alla dataset som testats i detta experiment.

Fraudulent pages are a danger to which all web users are exposed. These pages have illegitimate purposes such as the theft of sensitive user information. There are a lot of tools available on the market today that are aimed at detecting malicious pages, however, these are not reliable enough and that is why there is still a lot of room for future improvement. Therefore, further analysis of the malicious pages and their characteristics is a key element in protecting users and in the future in eradicating this type of malicious page. A systematic review of the literature has been conducted to generate a list of features that can be used to detect malicious pages and that can ensure a high level of accuracy. During the development of the study, the different articles on the subject have been compared and analysed. For this process of analysis, thematic coding has been used, a qualitative method of analysis, which means that an in-depth understanding of ideas has been pursued. The document presents the already cited list of characteristics as well as offering suggestions and ideas that can be used in the development of future

The perpetration of accounting fraud still remains a prevalent and significantly costly issue in today's business world. The names Enron, WorldCom, HealthSouth, and Madoff are still all too recent reminders of the devastating cost of financial statement fraud. Management accountants, as preparers of these statements, are in the best position to detect such fraud. Yet there exists no current measurement instrument or methodology designed to measure a management accountant's intention to report fraud. The primary purpose of this study was to investigate the beliefs, concepts, and antecedents that provide the motivation to, or the deterrent from, the reporting of fraudulent accounting activity when witnessed by professional management accountants, and develop an instrument that might measure that motivation. The theoretical basis that framed this research was the Theory of Planned Behavior which provides for an analysis of a participant's attitude, subjective norm, and perceived behavioral control in the development of the intention to perform a specific behavior. The population studied was the U.S. membership of the Institute of Management Accountants, and grant assistance and support was provided by the Institute's Research Foundation. The sample from this population formed a very appropriate representation of experienced, professional management accountants. . No previous research involving this population with the application of the Theory of Planned Behavior and the investigation of the reporting of fraudulent accounting activity had been conducted. Therefore, there were no existing survey instruments that could be applied. The development of an original survey questionnaire to specifically address this research was required. The distribution of this survey questionnaire resulted in 285 complete and usable responses. These responses measured the strength of the participant's positive or negative beliefs concerning the antecedents related to the three exogenous constructs of the Theory of Planned Behavior - attitude, subjective norm, and perceived behavioral control, and the endogenous construct of intention. Structural Equation Modeling (SEM) with measured variables was chosen as the methodology for the analysis of the results measured in the survey responses. Confirmatory Factor Analysis was applied to each construct individually, and construct items were modified to obtain the most reasonable model fit, validity, and reliability. Items were combined into composites to represent the constructs of interest in the theory, as measured by the survey. The relations among the constructs of the Theory of Planned Behavior were then specified using these composites in an SEM model. The results of the data and the findings of the SEM model indicated that professional management accountants form a strong positive intention to report the witnessing of accounting fraud. The positive beliefs that formed the exogenous variables that showed statistically significant effects on the endogenous variable of the formation of a positive intention to report fraudulent accounting activity were: support of the system of internal control, prevention of financial loss, retention of the integrity and ethical values of the profession, perceived support of significant others, and limited impediment due to fear of retaliation. A surprising result was that 32% of all respondents indicated a lack of easy/any access to an anonymous fraud reporting hotline, which is an issue for further research. This study provides additional insight into the concepts, beliefs, and antecedents that form a professional management accountant's intention to report fraudulent accounting activity. The study also presents the basis of a preliminary instrument for the measurement of the intention of management accountants to report fraudulent accounting activity. Further research is suggested for the identification of additional concepts, antecedents, and beliefs related to fraud reporting and for the development of an even more effective measurement instrument.

E-commerce has seen a rapid growth the last two decades, making it easy for customers to shop wherever they are. The growth has also led to new kinds of fraudulent activities affecting the customers. To make customers feel safe while shopping online, companies like Resurs Bank are implementing different kinds of fraud filters to freeze transactions that are thought to be fraudulent. The latest type of fraud filter is based on machine learning. While this seems to be a promising technology, data and algorithms need to be tuned properly to the task at hand. This thesis project gives a proof of concept of realizing a machine learning based fraud filter for Resurs Bank. Based on a literature study, available data and explainability requirements, this work opts for a supervised learning approach based on Random Forests with a sliding window to overcome concept drift. The inherent class imbalance of the setting makes the area-under-the-receiver operating-curve a suitable metric. This approach provided promising results that a machine learning based fraud filter can add value to companies like Resurs Bank. An alternative approach on how to incorporate non-numerical features by using recurrent neural networks (RNN) was implemented and compared. The non-numerical feature was transformed by a pre-trained RNN-model to a numerical representation that reflects the features suspiciousness. This new numerical feature was then included in the Random Forest model and the result demonstrated that this approach can add valuable insight to the fraud detection field.

Fraudulent automobile insurance claims are not only a loss for insurance companies, but also for their policyholders. In order for insurance companies to prevent significant loss from false claims, they must raise their premiums for the policyholders. The goal of this research is to develop a decision making algorithm to determine whether a claim is classified as fraudulent based on the observed characteristics of a claim, which can in turn help prevent future loss. The data includes 923 cases of false claims, 14,497 cases of true claims and 33 describing variables from the years 1994 to 1996. To achieve the goal of this research, parametric and nonparametric methods are used to determine what variables play a major role in detecting fraudulent claims. These methods include logistic regression, the LASSO (least absolute shrinkage and selection operator) method, and Random Forests. This research concluded that a non-parametric Random Forests model classified fraudulent claims with the highest accuracy and best balance between sensitivity and specificity. Variable selection and importance are also implemented to improve the performance at which fraudulent claims are accurately classified.

碩士
中國文化大學
會計學系
102
The study proposed a novel mechanism for fraudulent financial statement detection. The mechanism consists of two essential parts: one is ensemble feature selection strategy and the other is decision tree. The ensemble feature selection strategy is performed by two techniques, namely t-test and logistic regression. Both of them were used to determine the essential features. After determine the essential features, the selected features were fed into decision tree to construct the forecasting model. The 198 research samples ranged from 2000 to 2010 were considered in this study. According to our research finding, the union ensemble strategy outperforms than other ensemble strategies. In addition, the study also examines the effectiveness of corporate governance indictors. The results indicated that the corporate governance indicators can improve the forecasting performance of the introduced model.

碩士
國立臺灣大學
會計學研究所
107
This study attempts to apply data mining techniques on detection of fraudulent financial statements, and investigate whether textual information has information gain for fraudulent financial statements detection. Considering the characteristics of fraud, this study uses Random Forest as data mining techniques to build fraud detection model. Structured variables are selected based on fraud triangle, and textual information is extracted from letter to shareholders and operation review in annual report. The result shows that Random Forest achieved higher classification accuracy than traditional regression model, and the text in annual report has no explicit information gain for distinguishing fraudulent and non-fraudulent companies. However, it is worth noting that the importance of uncertain words in annual report ranks 13 among 83 variables. This implies that tentative words in annual report may be regarded as an important indicator to fraudulent financial statement occurrence.

碩士
國立臺灣大學
資訊工程學研究所
107
The main purpose of this thesis is to propose a model that can detect whether a phone number is a fraud in real-time. There are two problems in detecting fraud. Some methods can only apply at the same time interval as training data. On the other hand, a model that can apply to a new phone number have low precision. We propose a modularized call representation and detection model. By two-phases training, our model can generate call representations and uses the call representations to detect fraud. In the first phase, call behavior prediction training allows model generating call representation containing rich information. We then train a simple classifier to detect fraud based on the call representation. Our model outperforms the random baseline and beats baseline model which lacking the call behavior module. As for future work, multi phone number modeling can be used to detect complex fraud because Some fraud is cooperating between several phone numbers.

碩士
中原大學
電機工程研究所
105
Abstract In this thesis, we propose a face detection scheme with mask detection to prevent fraudulent use of ATM cards to increase safety for application of ATM. The purpose of our scheme is to solve the following problem. In ATM application, criminal''s face information can''t be recorded, because they usually use someone''s ATM card and deliberately cover their face. First, we open webcam to capture a live video and detect the user''s face portion by training cascading classifier for human face with Viola-Jones algorithm. Second, the user''s face image is transformed grayscale from RGB space. The grayscales image are blurred and sharpened to get images of face edge and facial features. These images are combined to detect if it is a mask image. Finally, we judge the threshold to accurately distinguish whether the face wearing a mask. In this thesis, the results of our research are as follows: 1. Reduce misjudgment : The mask detection solves the misjudgment of face detection. 2. Increase security of personal property : The detection system prevent lost cards from being used by others.

碩士
國立中正大學
會計與資訊科技研究所碩士在職專班
104
Financial statement fraud causes the society to suffer losses. The research is combining data mining techniques and ontology to provide relevance information for decision makers. The results will be great help to accountants and auditors for detecting financial statement fraud. In this study, the samples that conform to the definition of financial statement fraud companies are selected from Class-Action Litigation or Arbitration Ongoing Cases in Securities and Futures Investors Protection Center, The Judicial Yuan Of The Republic of China Law and Regulations Retrieving System, and news media. This study collect 31 companies who have involved in financial statements fraud, as well as 93 companies who have not during 2002-2016 as paired samples (1:3). Our analysis procedures are: First, using financial variables that previous studies had used to measure financial statements fraud as initial ontology of financial statement fraud; Second, followed by a decision tree data mining algorithms and randomforest data mining algorithms the important variables are selected; Third, we use decision tree, artificial neural network, and support vector machines of data mining algorithms to assess the accuracy of classification; Fourth, we establish criteria based on the decision tree to judge whether the enterprise faced financial statement fraud; At last, we build ontology knowledge of financial statement fraud. The proposed early warning model for financial statement fraud with ontology knowledge will provide convinced pattern and typologies of financial statement fraud.

abstract: Using historical data from the third-party payment acquiring industry, I develop a statistical model to predict the probability of fraudulent transactions by the merchants. The model consists of two levels of analysis – the first focuses on fraud detection at the store level, and the second focuses on fraud detection at the merchant level by aggregating store level data to the merchant level for merchants with multiple stores. My purpose is to put the model into business operations, helping to identify fraudulent merchants at the time of transactions and thus mitigate the risk exposure of the payment acquiring businesses. The model developed in this study is distinct from existing fraud detection models in three important aspects. First, it predicts the probability of fraud at the merchant level, as opposed to at the transaction level or by the cardholders. Second, it is developed by applying machine learning algorithms and logistical regressions to all the transaction level and merchant level variables collected from real business operations, rather than relying on the experiences and analytical abilities of business experts as in the development of traditional expert systems. Third, instead of using a small sample, I develop and test the model using a huge sample that consists of over 600,000 merchants and 10 million transactions per month. I conclude this study with a discussion of the model’s possible applications in practice as well as its implications for future research.
Dissertation/Thesis
Doctoral Dissertation Business Administration 2015

abstract: Due to the growing popularity of the Internet and smart mobile devices, massive data has been produced every day, particularly, more and more users’ online behavior and activities have been digitalized. Making a better usage of the massive data and a better understanding of the user behavior become at the very heart of industrial firms as well as the academia. However, due to the large size and unstructured format of user behavioral data, as well as the heterogeneous nature of individuals, it leveled up the difficulty to identify the SPECIFIC behavior that researchers are looking at, HOW to distinguish, and WHAT is resulting from the behavior. The difference in user behavior comes from different causes; in my dissertation, I am studying three circumstances of behavior that potentially bring in turbulent or detrimental effects, from precursory culture to preparatory strategy and delusory fraudulence. Meanwhile, I have access to the versatile toolkit of analysis: econometrics, quasi-experiment, together with machine learning techniques such as text mining, sentiment analysis, and predictive analytics etc. This study creatively leverages the power of the combined methodologies, and apply it beyond individual level data and network data. This dissertation makes a first step to discover user behavior in the newly boosting contexts. My study conceptualize theoretically and test empirically the effect of cultural values on rating and I find that an individualist cultural background are more likely to lead to deviation and more expression in review behaviors. I also find evidence of strategic behavior that users tend to leverage the reporting to increase the likelihood to maximize the benefits. Moreover, it proposes the features that moderate the preparation behavior. Finally, it introduces a unified and scalable framework for delusory behavior detection that meets the current needs to fully utilize multiple data sources.
Dissertation/Thesis
Doctoral Dissertation Business Administration 2019

This thesis is dealing with problems of creative accounting, with the access to its identification and utilization from the management position. The theoretical part defines the term of creative accounting. Moreover, it introduces possible readers into the fraudulent accounting and techniques of creative accounting. Furthermore, this thesis deals with circumstances that lead to the origin creativity. To add to this, this work addresses the psychological and behavioural point of view on the creativity. The main aim of the practical part is to answer the question of following hypothesis: The management of chosen accounting unit obligingly reacts on motivation which minimizes corporate income tax.

碩士
國立政治大學
會計學系
104
Due to the severe impacts caused by fraudulent financial reporting, securities regulatory commissions in most countries put much emphasis on maintaining the order of the capital markets and protecting the investors’ interests. In order to realize the factors of financial statement fraud, especially for China listed companies, and build the detecting model for the financial statements users, I select some listed companies punished by the government during the period 2007-2014 as the samples in this dissertation. Then, I use logistic regression model to test which variables are significant to fraudulent financial reporting, and the results show that the discretionary revenue and Z"-Score do not have impact on it. On the contrary, the percentage of independent directors, pressure from avoiding being “ST”, inventory turnover, accounts receivable turnover, and percentage of income from main operation are significantly relevant to fraudulent financial reporting. Moreover, when including these significant variables in the detecting model, the accuracy of the model can up to 53.31 percent.

No mundo contemporâneo, crimes econômicos e fraudes financeiras assumem diferentes formas, características e modalidades. A globalização e o dinâmico desenvolvimento tecnológico, tornaram sofisticados e complexos os crimes e fraudes, pois fragilizam mecanismos de defesas e controles internos devido a rapidez com que as mudanças organizacionais ocorrem e contribuem para elevar vulnerabilidades e riscos na gestão de contratos terceirizados. Os crimes e fraudes praticados durante a vigência de contratos, sejam privados ou públicos, evidenciam conflitos de interesses, desvios de condutas, oportunismos e desprezo aos valores éticos realizados por responsáveis que deveriam controlar acordos comerciais, licitações, seleções de fornecedores e/ou produtos, revelando um perfil fraudador com forte atuação predatória. A frágil, ou limitada, capacidade dos controles internos preventivos e a evidente manipulação das três linhas de defesa em todos os segmentos e portes empresariais ratificam, infelizmente, a elevação dos casos de fraudes e de crimes econômicos. Neste contexto, esta pesquisa procurou identificar riscos inerentes aos contratos e características do perfil fraudador responsável por anular controles e manipular linhas de defesa na gestão de contratos, estabelecendo o nexo causal entre a prática criminosa e a exposição aos riscos contratuais. Fundamentado nesse propósito, foram realizadas pesquisas específicas sobre os tipos de contratos impactados, características dos perfis dos fraudadores e identificação das principais medidas protecionistas implementadas para mitigar fraudes e crimes econômicos contratuais. Finalmente, espera-se que esta Dissertação concorra para a conscientização de empresários, gestores e, principalmente, auditores, sobre a importância em disseminar para os atores envolvidos na gestão de contratos terceirizados metodologias e ferramentas relacionadas à detecção, à prevenção, ao monitoramento e ao tratamento de riscos, alinhadas com regras de compliance específicas para os riscos contratuais inerentes, que permitam preservar a imagem da empresa, proteger investimentos, garantir operações e continuidade do negócio.
In the contemporary world, economic crimes and financial fraud take on different forms, characteristics and modalities. Globalization and dynamic technological development have made sophisticated and complex crimes and frauds as they weaken internal defenses and controls because of the rapidity with which organizational changes occur and contribute to the elevation of vulnerabilities and risks in the management of outsourced contracts. Crimes and fraud committed during the term of contracts, whether private or public, show conflicts of interest, misconduct, opportunism and contempt for the ethical values made by managers who should control commercial agreements, bids, supplier selections and / or products, Revealing a predatory fraud profile. The fragile or limited capacity of the internal preventive controls and the evident manipulation of the three lines of defense in all segments and sizes of business unfortunately ratify the increase of cases of fraud and economic crimes. In this context, this research sought to identify risks inherent in the contracts and characteristics of the fraud profile responsible for annulling controls and manipulating lines of defense in contract management, establishing the causal link between criminal practice and exposure to contractual risks. Based on this purpose, specific research was carried out on the types of contracts impacted, characteristics of fraudster profiles and identification of the main protectionist measures implemented to mitigate fraud and economic contractual crimes. Finally, it is expected that this Dissertation will contribute to the awareness of entrepreneurs, managers and, especially, auditors, about the importance of disseminating to the actors involved in the management of outsourced contracts methodologies and tools related to the detection, prevention, monitoring and Risk treatment in line with specific compliance rules for the inherent contractual risks that can preserve the company’s image, protect investments, guarantee operations and business continuity.

碩士
世新大學
資訊管理學研究所(含碩專班)
97
The trend of liberalization and internationalization on global financial market brings in booming development in credit market. In order to achieve high volume in issuing credit cards and be a leading role in the credit market, bank employees who issue credit cards trend to adopt more flexible standards when evaluating applicants’ qualifications. These situations may accelerate the ratio of fraudulent applications and the existence of ghost accounts. Therefore, how to detect and prevent fraud case at the time of approval to reduce the risk of issuing credit cards becomes vital to banks. 　　The Rule-Based Expert Systems utilizes the technique of information system to construct an automatically evaluating system, to either assist with or replace the evaluation executed by professional workers. Through the strength of the Rule-Based Expert Systems to offset the weakness of manpower, it will effectively reduce the risk of issuing credit cards and achieve a better result of evaluation. At the same time, when applying the Service Oriented Architecture , we can utilize its characteristics of Loosely Coupled and Process Centric to help the issuing banks effectively integrate their internal business resources with the stages of its growth and present its competitive strength in today’s versatile and challenging business environments. In this thesis, I will utilize Web service as a tool and apply Service Oriented Architecture to construct Rule-Based Expert Systems and design “Credit Card Fraudulent Application Detecting System” to assist banks and satisfy its various needs in modern business environments.