This study examines the predictive power of restricted stock and stock option compensation on the enforcement of an Accounting and Auditing Enforcement Release. Since executives have seen substantial increases in the amount of equity incentive awards, this may incentivize management to commit financial reporting misconduct to boost the value of these awards. The magnitude of the incentive to commit financial reporting misconduct is hypothesized to be more pronounced with stock option compensation when compared with restricted stock compensation. The analysis for the 1992-2012 time period shows that the amount of stock option compensation has a positive relationship with the probability of an AAER enforcement while no such relationship exists for restricted stock. When examining this predictive probability relationship during 1992-2002 and 2003-2012, the evidence is mixed. While the amount of stock option compensation displays a positive relationship with the predicted probability of an AAER enforcement, restricted stock has a positive relationship in 1992-2002 and a negative relationship in 2003-2012.

Ontologies are a key factor of Information management as they provide a common representation to any domain. Historically, finance domain has suffered from a lack of efficiency in managing vast amounts of financial data, a lack of communication and knowledge sharing between analysts. Particularly, with the growth of fraud in financial markets, cases are challenging, complex, and involve a huge volume of information. Gathering facts and evidence is often complex. Thus, the impetus for building a financial fraud ontology arises from the continuous improvement and development of financial market surveillance systems with high analytical capabilities to capture frauds which is essential to guarantee and preserve an efficient market.This thesis proposes an ontology-based approach for financial market surveillance systems. The proposed ontology acts as a semantic representation of mining concepts from unstructured resources and other internet sources (corpus). The ontology contains a comprehensive concept system that can act as a semantically rich knowledge base for a market monitoring system. This could help fraud analysts to understand financial fraud practices, assist open investigation by managing relevant facts gathered for case investigations, providing early detection techniques of fraudulent activities, developing prevention practices, and sharing manipulation patterns from prosecuted cases with investigators and relevant users. The usefulness of the ontology will be evaluated through three case studies, which not only help to explain how manipulation in markets works, but will also demonstrate how the ontology can be used as a framework for the extraction process and capturing information related to financial fraud, to improve the performance of surveillance systems in fraud monitoring. Given that most manipulation cases occur in the unregulated markets, this thesis uses a sample of fraud cases from the unregulated markets. On the empirical side, the thesis presents examples of novel applications of text-mining tools and data-processing components, developing off-line surveillance systems that are fully working prototypes which could train the ontology in the most recent manipulation techniques.

Ukraine is quite new country, which faces early stages of its development. The financial market of the country has passed through different and challenging times for these 20 years and still has to choose several essential factors for the further development. The existence of financial frauds in Ukraine could be explained by lack of knowledge and information in the country as well as low level of trust to the government. The case of JSC "MMM" and Mr. Mavrodi is the best well-known example of Ponzi scheme in Ukraine and all post-Soviet countries, which gives the possibility to analyze the main features of its consequences.

Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2017-05-19T12:43:37Z No. of bitstreams: 1 Davenilcio Luiz de. Souza_.pdf: 539499 bytes, checksum: cf86851f0b7523f3b7d78589539fdbcb (MD5) / Made available in DSpace on 2017-05-19T12:43:37Z (GMT). No. of bitstreams: 1 Davenilcio Luiz de. Souza_.pdf: 539499 bytes, checksum: cf86851f0b7523f3b7d78589539fdbcb (MD5) Previous issue date: 2017-03-13 / Nenhuma / Os crimes de lavagem de dinheiro têm provocado grandes perdas aos países e a seus sistemas financeiros, o volume de dados em transações digitais representa dificuldade para a detecção deste tipo de ilícito. As auditorias em dados financeiros mostram-se limitadas na identificação de fraudes, pois em grande parte, ainda são realizadas com dados coletados por amostragem e incapazes de identificar as situações de delito em tempo real. Este trabalho, visando auxiliar no atendimento a esta lacuna, tem por objetivo propor um método estatístico de monitoramento por Cartas de Controle multivariadas, com base na Lei de Benford, para a detecção de suspeitas de fraude em lançamentos financeiros, entre eles os devidos à lavagem de dinheiro. Foi definido um modelo conceitual com distribuição de probabilidades representando dados oriundos de lançamentos financeiros, e adotada a suposição de que aderem a distribuição da Lei de Benford. Posteriormente foi considerada a distribuição empírica, estimada a partir dos próprios dados e dois procedimentos foram testados para verificar as suspeitas de fraude por lavagem de dinheiro utilizando a avaliação dos primeiros dígitos significativos: A Carta de Controle multivariada _2 e a Carta de Controle multivariada T2 de Hotelling. Foram simulados dados com auxílio do software R-Project até a ocorrência do 50.000o sinal. Foram avaliados casos simulados e reais, com o fim de exemplificar a operação do método. A partir da simulação, as duas Cartas de Controle testadas foram avaliadas quanto ao ARL, isto é, o número médio de observações até sinalizar que a série passou a operar em um estado fora de controle, o que significa a suspeita de lançamentos fraudulentos. Após aplicação do método de análise retrospectiva, com base nas proporções dos primeiros dígitos de Benford em lançamentos financeiros da campanha para Prefeito em 2016, não foram evidenciadas suspeitas de fraude nos dados obtidos junto ao sítio do Tribunal Superior Eleitoral (TSE). Em um conjunto de dados de uma instituição financeira, foram observados sinais de divergência entre as frequências dos primeiros dígitos nos lançamentos e nos valores esperados, porém os pontos além dos limites de controleidentificados encontram-se em um período próximo nas três análises realizadas, concentrando os dados de investigação para a auditoria financeira. A contribuição acadêmica deu-se pelo desenvolvimento de um modelo de aplicação de Cartas de Controle multivariadas e da Lei de Benford, com uma abordagem inovadora do controle estatístico de processos voltado à área financeira, utilizando recurso computacional acessível, de fácil processamento, confiável e preciso, que permite aprimoramento por novas abordagens acadêmicas. No que tange à contribuição à sociedade, se dá pelo uso do modelo por entidades que atuam com movimentações financeiras e pela comunidade, em dados de organizações civis e estatais divulgados nos canais de informação, de modo a proporcionar a prática cidadã pelo acesso à análise e a constatação da idoneidade dos fatos e dos dados. / Large losses are generated in the countryes financial systems, by money laundering. The volume of financial data is big issue to identify digital crime and money laundering. Audits in financial data have limitations in detecting fraud, in large part it is still performed in a traditional way, data are collected by sampling and often unable to identify a real-time crime situation. This research is aiming to serve in addressing this gap, to propose an monitoring statistical method, from multivariate control chart based on Benford’s law for detecting suspicious of fraud in financial data, including those due to money laundering. It was initially defined as a conceptual model in order to determine the type of probability distribution that represents data from financial launches. It was adopted an assumption that this type of data adheres to the Benford’s Law distribution. Subsequently, an empirical distribution was obtained, estimated from the own data. Two procedures were tested to verify a suspected money laundering fraud through the significant first-digit assessment: The Multivariate 2 Control Chart and the Multivariate Hotelling’s T2 Control Chart. Data were simulated using the R-Project software until the occurrence of the 50.000o signal. Finally, the simulation procedures were applied to real data in order to exemplify the method operationally. From the simulation, the two Control Charts tested were evaluated for ARL, that is, average number of observations until the signaling that the series started to operate in an out-of-control state, which it means suspicious of fraudulent launches. The application of the retrospective analysis method in the financial launchings of county’s campaign from 2016 Elections in five capitals of Brazil, based on the expected proportions from the first digit given by Benford’s Law, no suspicions fraud were evidenced in the data obtained from the site of Tribunal Superior Eleitoral (TSE). Considering the application in a set of data from a financial institution, signs of divergence between the frequencies of the first digits of the entries and the expected values were observed, but these points beyond the identified limits are close in all three analyzes. Indicating the period of the data which ones the audit will focus in a further investigation. Academic contribution is identified by developing a multivariate Control Chart together the Benford’s law in an application model with an innovative approach to the statistical process control aimed at the financial area,using accessible, easy to process, reliable and accurate computational resources that allow improvement through new academic approaches. As regard to the contribution to society, it is given the opportunity of applying the model by financial entities and the community in the data of civil and state organizations, disclosed in the information channels in order to provide access to analysis and verification of the suitability of facts and data by citizen practice.

由於政經環境之變遷、公司治理的缺漏和外部監理機制之失調，常導致重大金融犯罪之發生，與其惡害卻由全民負擔之不公現象。於是除嚴刑峻罰外，奠基於任何人均不得從犯罪中獲利之犯罪所得剝奪理念與制度設計，遂於二ＯＯ四年金融七法修法時被廣泛納入。惟歷經一段期間之適用後，其法實效性如何？有無源於其他刑事法制無從配合，或囿於司法實務判解之困頓，所導致的扞格？部分國際公約與其他國家之相關法制設計及運作理念，有無值得比較、參研之處，均殊值探研。 　　本文嘗試先掌握金融犯罪之特性，與近來金融犯罪防制法規之演變。其次，再就我國犯罪所得剝奪法制沿革、犯罪所得之界定、計算為研析，並探索犯罪所得剝奪法制在預防、打擊與抗制金融犯罪等之必要性，以及其應通過之憲法基權保障檢驗。再者，則希能透過偵審案例，探究研現階段我國金融犯罪防制法規，在犯罪所得之暫時保全與終局剝奪上所面臨之實務困境及問題；並瞭解部分重要之國際公約與美、英、日等國家有關法制之設計。最後，則期能歸結相關問題與爭議，並融合法制建構、實務運作、外國法制借鏡等數個層面，提出可能之解決途徑或修法建議。 / Political and economic changes, incomplete of corporate governance, and imbalance of external supervision mechanism are all reasons for occurrence of major financial fraud. The losses and costs of major financial fraud, in general, are always enormous. Unfortunately, most people, instead of offenders, need to bear the huge losses. As a result, except the strategy of severe punishment, the idea and regulations on deprivation proceeds of crime were introduced to combat these problems in 2004. However, after a period of practicing, how about the application and practice of regulations on deprivation proceeds of crime is. Therefore, we are concerned about: are there any problems or difficulties resulting from criminal legal system and the practice of precedent itself? What we can learn from international conventions and other countries’ similar legal system? The thesis, first of all, attempts to figure out the feature of major financial fraud and the changes of financial regulations. Secondly, we try to explore the history of regulations on deprivation proceeds of crime, the definition and the calculation of proceeds of crime, and whether the regulations on deprivation proceeds of crime are essential for preventing and against major financial fraud or not. Meanwhile, in order to guarantee and protect the fundamental rights of people, we also hope to exam the regulations on deprivation proceeds of crime by the concepts of constitution. In additions, according to the case study, the thesis also longs for exploring what are the practical problems and dilemmas for current regulations on temporary seizure and final forfeiture procedures. At the same time, comparing with the international conventions and other countries’ similar legal system on laundering, search, freeze, seizure and confiscation of the proceeds from crime is also important and useful for this study. Finally, after concluding the relative problems and debates about this topic, of course, the paper hopes to propose a possible approach or legal amendment by integrating legal system modification, legal practice, and foreign legal system.

Financial fraud rampages onwards seemingly uncontained. The annual cost of fraud in the UK is estimated to be as high as £193bn a year [1] . From a data science perspective and hitherto less explored this thesis demonstrates how the use of linguistic features to drive data mining algorithms can aid in unravelling fraud. To this end, the spotlight is turned on Financial Statement Fraud (FSF), known to be the costliest type of fraud [2]. A new corpus of 6.3 million words is composed of102 annual reports/10-K (narrative sections) from firms formally indicted for FSF juxtaposed with 306 non-fraud firms of similar size and industrial grouping. Differently from other similar studies, this thesis uniquely takes a wide angled view and extracts a range of features of different categories from the corpus. These linguistic correlates of deception are uncovered using a variety of techniques and tools. Corpus linguistics methodology is applied to extract keywords and to examine linguistic structure. N-grams are extracted to draw out collocations. Readability measurement in financial text is advanced through the extraction of new indices that probe the text at a deeper level. Cognitive and perceptual processes are also picked out. Tone, intention and liquidity are gauged using customised word lists. Linguistic ratios are derived from grammatical constructs and word categories. An attempt is also made to determine ‘what’ was said as opposed to ‘how’. Further a new module is developed to condense synonyms into concepts. Lastly frequency counts from keywords unearthed from a previous content analysis study on financial narrative are also used. These features are then used to drive machine learning based classification and clustering algorithms to determine if they aid in discriminating a fraud from a non-fraud firm. The results derived from the battery of models built typically exceed classification accuracy of 70%. The above process is amalgamated into a framework. The process outlined, driven by empirical data demonstrates in a practical way how linguistic analysis could aid in fraud detection and also constitutes a unique contribution made to deception detection studies.

Différents types de risques existent dans le domaine financier, tels que le financement du terrorisme, le blanchiment d’argent, la fraude de cartes de crédit, la fraude d’assurance, les risques de crédit, etc. Tout type de fraude peut entraîner des conséquences catastrophiques pour des entités telles que les banques ou les compagnies d’assurances. Ces risques financiers sont généralement détectés à l'aide des algorithmes de classification. Dans les problèmes de classification, la distribution asymétrique des classes, également connue sous le nom de déséquilibre de classe (class imbalance), est un défi très commun pour la détection des fraudes. Des approches spéciales d'exploration de données sont utilisées avec les algorithmes de classification traditionnels pour résoudre ce problème. Le problème de classes déséquilibrées se produit lorsque l'une des classes dans les données a beaucoup plus d'observations que l’autre classe. Ce problème est plus vulnérable lorsque l'on considère dans le contexte des données massives (Big Data). Les données qui sont utilisées pour construire les modèles contiennent une très petite partie de groupe minoritaire qu’on considère positifs par rapport à la classe majoritaire connue sous le nom de négatifs. Dans la plupart des cas, il est plus délicat et crucial de classer correctement le groupe minoritaire plutôt que l'autre groupe, comme la détection de la fraude, le diagnostic d’une maladie, etc. Dans ces exemples, la fraude et la maladie sont les groupes minoritaires et il est plus délicat de détecter un cas de fraude en raison de ses conséquences dangereuses qu'une situation normale. Ces proportions de classes dans les données rendent très difficile à l'algorithme d'apprentissage automatique d'apprendre les caractéristiques et les modèles du groupe minoritaire. Ces algorithmes seront biaisés vers le groupe majoritaire en raison de leurs nombreux exemples dans l'ensemble de données et apprendront à les classer beaucoup plus rapidement que l'autre groupe. Dans ce travail, nous avons développé deux approches : Une première approche ou classifieur unique basée sur les k plus proches voisins et utilise le cosinus comme mesure de similarité (Cost Sensitive Cosine Similarity K-Nearest Neighbors : CoSKNN) et une deuxième approche ou approche hybride qui combine plusieurs classifieurs uniques et fondu sur l'algorithme k-modes (K-modes Imbalanced Classification Hybrid Approach : K-MICHA). Dans l'algorithme CoSKNN, notre objectif était de résoudre le problème du déséquilibre en utilisant la mesure de cosinus et en introduisant un score sensible au coût pour la classification basée sur l'algorithme de KNN. Nous avons mené une expérience de validation comparative au cours de laquelle nous avons prouvé l'efficacité de CoSKNN en termes de taux de classification correcte et de détection des fraudes. D’autre part, K-MICHA a pour objectif de regrouper des points de données similaires en termes des résultats de classifieurs. Ensuite, calculez les probabilités de fraude dans les groupes obtenus afin de les utiliser pour détecter les fraudes de nouvelles observations. Cette approche peut être utilisée pour détecter tout type de fraude financière, lorsque des données étiquetées sont disponibles. La méthode K-MICHA est appliquée dans 3 cas : données concernant la fraude par carte de crédit, paiement mobile et assurance automobile. Dans les trois études de cas, nous comparons K-MICHA au stacking en utilisant le vote, le vote pondéré, la régression logistique et l’algorithme CART. Nous avons également comparé avec Adaboost et la forêt aléatoire. Nous prouvons l'efficacité de K-MICHA sur la base de ces expériences. Nous avons également appliqué K-MICHA dans un cadre Big Data en utilisant H2O et R. Nous avons pu traiter et analyser des ensembles de données plus volumineux en très peu de temps / There are different types of risks in financial domain such as, terrorist financing, money laundering, credit card fraudulence and insurance fraudulence that may result in catastrophic consequences for entities such as banks or insurance companies. These financial risks are usually detected using classification algorithms. In classification problems, the skewed distribution of classes also known as class imbalance, is a very common challenge in financial fraud detection, where special data mining approaches are used along with the traditional classification algorithms to tackle this issue. Imbalance class problem occurs when one of the classes have more instances than another class. This problem is more vulnerable when we consider big data context. The datasets that are used to build and train the models contain an extremely small portion of minority group also known as positives in comparison to the majority class known as negatives. In most of the cases, it’s more delicate and crucial to correctly classify the minority group rather than the other group, like fraud detection, disease diagnosis, etc. In these examples, the fraud and the disease are the minority groups and it’s more delicate to detect a fraud record because of its dangerous consequences, than a normal one. These class data proportions make it very difficult to the machine learning classifier to learn the characteristics and patterns of the minority group. These classifiers will be biased towards the majority group because of their many examples in the dataset and will learn to classify them much faster than the other group. After conducting a thorough study to investigate the challenges faced in the class imbalance cases, we found that we still can’t reach an acceptable sensitivity (i.e. good classification of minority group) without a significant decrease of accuracy. This leads to another challenge which is the choice of performance measures used to evaluate models. In these cases, this choice is not straightforward, the accuracy or sensitivity alone are misleading. We use other measures like precision-recall curve or F1 - score to evaluate this trade-off between accuracy and sensitivity. Our objective is to build an imbalanced classification model that considers the extreme class imbalance and the false alarms, in a big data framework. We developed two approaches: A Cost-Sensitive Cosine Similarity K-Nearest Neighbor (CoSKNN) as a single classifier, and a K-modes Imbalance Classification Hybrid Approach (K-MICHA) as an ensemble learning methodology. In CoSKNN, our aim was to tackle the imbalance problem by using cosine similarity as a distance metric and by introducing a cost sensitive score for the classification using the KNN algorithm. We conducted a comparative validation experiment where we prove the effectiveness of CoSKNN in terms of accuracy and fraud detection. On the other hand, the aim of K-MICHA is to cluster similar data points in terms of the classifiers outputs. Then, calculating the fraud probabilities in the obtained clusters in order to use them for detecting frauds of new transactions. This approach can be used to the detection of any type of financial fraud, where labelled data are available. At the end, we applied K-MICHA to a credit card, mobile payment and auto insurance fraud data sets. In all three case studies, we compare K-MICHA with stacking using voting, weighted voting, logistic regression and CART. We also compared with Adaboost and random forest. We prove the efficiency of K-MICHA based on these experiments

增長層級式自我組織映射網路(GHSOM)屬於一種非監督式類神經網路，為自我組織映射網路(SOM)的延伸，擅長於對樣本分群，以輔助分析樣本族群裡的共同特徵，並且可以透過族群間存在的空間關係假設來建立分類器，進而辨別出異常的資料。 因此本研究提出一個創新的對偶方法(即為一個建立決策支援系統架構的方法)分別對舞弊與非舞弊樣本分群，首先兩類別之群組會被配對，即辨識某一特定無弊群體的非舞弊群體對照組，針對這些配對族群，套用基於不同空間假設所設立的分類規則以檢測舞弊與非舞弊群體中是否有存在某種程度的空間關係，此外並對於舞弊樣本的分群結果加入特徵萃取機制。分類績效最好的分類規則會被用來偵測受測樣本是否有舞弊的嫌疑，萃取機制的結果則會用來標示有舞弊嫌疑之受測樣本的舞弊行為特徵以及相關的輸入變數，以做為後續的決策輔助。 更明確地說，本研究分別透過非舞弊樣本與舞弊樣本建立一個非舞弊GHSOM樹以及舞弊GHSOM樹，且針對每一對GHSOM群組建立分類規則，其相應的非舞弊/舞弊為中心規則會適應性地依循決策者的風險偏好最佳化調整規則界線，整體而言較優的規則會被決定為分類規則。非舞弊為中心的規則象徵絕大多數的舞弊樣本傾向分布於非舞弊樣本的周圍，而舞弊為中心的規則象徵絕大多數的非舞弊樣本傾向分布於舞弊樣本的周圍。 此外本研究加入了一個特徵萃取機制來發掘舞弊樣本分群結果中各群組之樣本資料的共同特質，其包含輸入變數的特徵以及舞弊行為模式，這些資訊將能輔助決策者(如資本提供者)評估受測樣本的誠實性，輔助決策者從分析結果裡做出更進一步的分析來達到審慎的信用決策。 本研究將所提出的方法套用至財報舞弊領域(屬於財務舞弊偵測的子領域)進行實證，實驗結果證實樣本之間存在特定的空間關係，且相較於其他方法如SVM、SOM+LDA和GHSOM+LDA皆具有更佳的分類績效。因此顯示本研究所提出的機制可輔助驗證財務相關數據的可靠性。此外，根據SOM的特質，即任何受測樣本歸類到某特定族群時，該族群訓練樣本的舞弊行為特徵將可以代表此受測樣本的特徵推論。這樣的原則可以用來協助判斷受測樣本的可靠性，並可供持續累積成一個舞弊知識庫，做為進一步分析以及制定相關信用決策的參考。本研究所提出之基於對偶方法的決策支援系統架構可以被套用到其他使用財務數據為資料來源的財務舞弊偵測情境中，作為輔助決策的基礎。 / The Growing Hierarchical Self-Organizing Map (GHSOM) is extended from the Self-Organizing Map (SOM). The GHSOM’s unsupervised learning nature such as the adaptive group size as well as the hierarchy structure renders its availability to discover the statistical salient features from the clustered groups, and could be used to set up a classifier for distinguishing abnormal data from regular ones based on spatial relationships between them. Therefore, this study utilizes the advantage of the GHSOM and pioneers a novel dual approach (i.e., a proposal of a DSS architecture) with two GHSOMs, which starts from identifying the counterparts within the clustered groups. Then, the classification rules are formed based on a certain spatial hypothesis, and a feature extraction mechanism is applied to extract features from the fraud clustered groups. The dominant classification rule is adapted to identify suspected samples, and the results of feature extraction mechanism are used to pinpoint their relevant input variables and potential fraud activities for further decision aid. Specifically, for the financial fraud detection (FFD) domain, a non-fraud (fraud) GHSOM tree is constructed via clustering the non-fraud (fraud) samples, and a non-fraud-central (fraud-central) rule is then tuned via inputting all the training samples to determine the optimal discrimination boundary within each leaf node of the non-fraud (fraud) GHSOM tree. The optimization renders an adjustable and effective rule for classifying fraud and non-fraud samples. Following the implementation of the DSS architecture based on the proposed dual approach, the decision makers can objectively set their weightings of type I and type II errors. The classification rule that dominates another is adopted for analyzing samples. The dominance of the non-fraud-central rule leads to an implication that most of fraud samples cluster around the non-fraud counterpart, meanwhile the dominance of fraud-central rule leads to an implication that most of non-fraud samples cluster around the fraud counterpart. Besides, a feature extraction mechanism is developed to uncover the regularity of input variables and fraud categories based on the training samples of each leaf node of a fraud GHSOM tree. The feature extraction mechanism involves extracting the variable features and fraud patterns to explore the characteristics of fraud samples within the same leaf node. Thus can help decision makers such as the capital providers evaluate the integrity of the investigated samples, and facilitate further analysis to reach prudent credit decisions. The experimental results of detecting fraudulent financial reporting (FFR), a sub-field of FFD, confirm the spatial relationship among fraud and non-fraud samples. The outcomes given by the implemented DSS architecture based on the proposed dual approach have better classification performance than the SVM, SOM+LDA, GHSOM+LDA, SOM, BPNN and DT methods, and therefore show its applicability to evaluate the reliability of the financial numbers based decisions. Besides, following the SOM theories, the extracted relevant input variables and the fraud categories from the GHSOM are applicable to all samples classified into the same leaf nodes. This principle makes that the extracted pre-warning signal can be applied to assess the reliability of the investigated samples and to form a knowledge base for further analysis to reach a prudent decision. The DSS architecture based on the proposed dual approach could be applied to other FFD scenarios that rely on financial numbers as a basis for decision making.