To see the other types of publications on this topic, follow the link: Detection of insurance fraud.
Dissertations / Theses on the topic 'Detection of insurance fraud'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Detection of insurance fraud.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Roberts, Terisa. "The use of credit scorecard design, predictive modelling and text mining to detect fraud in the insurance industry / Terisa Roberts." Thesis, North-West University, 2011. http://hdl.handle.net/10394/10347.
Full textAbstract:
The use of analytical techniques for fraud detection and the design of fraud detection systems have been topics of several research projects in the past and have seen varying degrees of success in their practical implementation. In particular, several authors regard the use of credit risk scorecards for fraud detection as a useful analytical detection tool. However, research on analytical fraud detection for the South African insurance industry is limited. Furthermore, real world restrictions like the availability and quality of data elements, highly unbalanced datasets, interpretability challenges with complex analytical techniques and the evolving nature of insurance fraud contribute to the on-going challenge of detecting fraud successfully. Insurance organisations face financial instability from a global recession, tighter regulatory requirements and consolidation of the industry, which implore the need for a practical and effective fraud strategy. Given the volumes of structured and unstructured data available in data warehouses of insurance organisations, it would be sensible for an effective fraud strategy to take into account data-driven methods and incorporate analytical techniques into an overall fraud risk assessment system. Having said that, the complexity of the analytical techniques, coupled with the effort required to prepare the data to support it, should be carefully considered as some studies found that less complex algorithms produce equal or better results. Furthermore, an over reliance on analytical models can underestimate the underlying risk, as observed with credit risk at financial institutions during the financial crisis. An attractive property of the structure of the probabilistic weights-of-evidence (WOE) formulation for risk scorecard construction is its ability to handle data issues like missing values, outliers and rare cases. It is also transparent and flexible in allowing the re-adjustment of the bins based on expert knowledge or other business considerations. The approach proposed in the study is to construct fraud risk scorecards at entity level that incorporate sets of intrinsic and relational risk factors to support a robust fraud risk assessment. The study investigates the application of an integrated Suspicious Activity Assessment System (SAAS) empirically using real-world South African insurance data. The first case study uses a data sample of short-term insurance claims data and the second a data sample of life insurance claims data. Both case studies show promising results. The contributions of the study are summarised as follows: The study identified several challenges with the use of an analytical approach to fraud detection within the context of the South African insurance industry. The study proposes the development of fraud risk scorecards based on WOE measures for diagnostic fraud detection, within the context of the South African insurance industry, and the consideration of alternative algorithms to determine split points. To improve the discriminatory performance of the fraud risk scorecards, the study evaluated the use of analytical techniques, such as text mining, to identify risk factors. In order to identify risk factors from large sets of data, the study suggests the careful consideration of both the types of information as well as the types of statistical techniques in a fraud detection system. The types of information refer to the categories of input data available for analysis, translated into risk factors, and the types of statistical techniques refer to the constraints and assumptions of the underlying statistical techniques. In addition, the study advocates the use of an entity-focused approach to fraud detection, given that fraudulent activity typically occurs at an entity or group of entities level.PhD, Operational Research, North-West University, Vaal Triangle Campus, 2011
2
Hradilová, Zuzana. "Pojistné podvody." Master's thesis, Vysoké učení technické v Brně. Ústav soudního inženýrství, 2014. http://www.nusl.cz/ntk/nusl-232859.
Full textAbstract:
This diploma thesis deals with problems of insurance fraud in the Czech Republic. The thesis is decided into the several separate parts. The teoretical part describes characteristics of insuracne fraud itselfs, its classification, profile of fraud perpetor and reason of committing instance fraud at all. The next part describes detection of insurance fraud and the subsecvent procedure in investigating insurance fraud. The goal of practical part of diploma thesis is analysis of insurance fraud and questionnaire survey. There will be describe the prevetion of insurance fraud and in the end, there will be several specific cases of insurance fraud.
3
Pražanová, Markéta. "Problematika pojistného podvodu v ČR." Master's thesis, Vysoká škola ekonomická v Praze, 2010. http://www.nusl.cz/ntk/nusl-75473.
Full textAbstract:
The insurance fraud is frequent type of criminality at the present time. The perpetrators of this crime cause heavy economic damages to insurance companies. Objective of the thesis called "The insurance fraud in the Czech Republic" is to evaluate the current state of the problem of insurance fraud in the Czech Republic from the perspective of insurance companies, law enforcement authorities and new legislation. As well to describe the way of detection and investigation, characterize the offender, analyze the most frequent cases, typical methods of committing insurance fraud and to evaluate the statistics and trends from previous years. In the thesis are explained the principles of detecting insurance fraud in insurance companies and the preventive measures. Part of the thesis is to identify weaknesses in the fight against the insurance fraud.
4
Konopíková, Marie. "Pojistné podvody." Master's thesis, Vysoká škola ekonomická v Praze, 2014. http://www.nusl.cz/ntk/nusl-205812.
Full textAbstract:
This thesis is focused on theme of insurance´s fraud, primarily from the legal aspects. The thesis consist of legislative of insurance fraud according to the Criminal Code, also including a list of punishment. The following part dedicate to active insurers fight against cheats, their investigation and using more effective instruments and measures of their prevention. The thesis doesn´t forget statistical data and development in detection of insurance fraud in last 5 years. There is also the judicature of High Court and the examples of practise.
5
Gažová, Iva. "Pojistné podvody." Master's thesis, Vysoké učení technické v Brně. Ústav soudního inženýrství, 2010. http://www.nusl.cz/ntk/nusl-232511.
Full textAbstract:
This diploma thesis deals with the problems of insurance fraud in our society. The thesis is divided into several relatively separate sections. The theoretical part describes a basic characteristic, classification and origins of insurance fraud and it deals with a general description of perpetrators of fraudulent actions. An analysis of fraudulent actions in life and non-life insurance is carried out in the theoretical part of the diploma thesis. This work characterises the importance and the mutual relationship between detection and investigation of fraudulent actions. It also highlights the facts which aid and abet insurance fraud. The aim of the practical part of the diploma thesis was to carry out an analysis of various insurance fraud cases in the realm of motor insurance according to the subject, object and the most frequent variants of fraudulent actions and consequently create a profile of the perpetrator of insurance fraud on the basis of the evaluation of the analysis. The practical case study of client’s expedient behaviour enables us to look on detection of the particular insurance fraud. The end of the diploma thesis deals with recommendations for the measures which should be taken to fight insurance fraud.
6
da, Rosa Raquel C. "An Evaluation of Unsupervised Machine Learning Algorithms for Detecting Fraud and Abuse in the U.S. Medicare Insurance Program." Thesis, Florida Atlantic University, 2018. http://pqdtopen.proquest.com/#viewpdf?dispub=10815097.
Full textAbstract:
The population of people ages 65 and older has increased since the 1960s and current estimates indicate it will double by 2060. Medicare is a federal health insurance program for people 65 or older in the United States. Medicare claims fraud and abuse is an ongoing issue that wastes a large amount of money every year resulting in higher health care costs and taxes for everyone. In this study, an empirical evaluation of several unsupervised machine learning approaches is performed which indicates reasonable fraud detection results. We employ two unsupervised machine learning algorithms, Isolation Forest, and Unsupervised Random Forest, which have not been previously used for the detection of fraud and abuse on Medicare data. Additionally, we implement three other machine learning methods previously applied on Medicare data which include: Local Outlier Factor, Autoencoder, and k-Nearest Neighbor. For our dataset, we combine the 2012 to 2015 Medicare provider utilization and payment data and add fraud labels from the List of Excluded Individuals/Entities (LEIE) database. Results show that Local Outlier Factor is the best model to use for Medicare fraud detection.
7
Minár, Tomáš. "Detekce pojistných podvodů." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2012. http://www.nusl.cz/ntk/nusl-223691.
Full textAbstract:
This thesis focuses on the area of detection of potential insurance frauds by using Business Intelligence (BI) and its practical application to real data of compulsory and accident insurance. It describes the basic concepts of insurance business, the individual layers of BI architecture, and a detailed description of the implementation process from data transformation through the use of advanced analytical methods to the presentation of acquired information.
8
Gill, Karen Ann. "Insurance fraud : causes, characteristics and prevention." Thesis, University of Leicester, 2014. http://hdl.handle.net/2381/29106.
Full textAbstract:
Although there is a growing volume of research on various kinds of fraud, relatively little has been written about insurance fraud. Even fewer studies have been undertaken on the prevention of insurance fraud. This study aims to fill this gap. It focuses not on large-scale corporate fraud but on individuals ‘fiddling’ their home, motor and travel policies. During the course of this study, the researcher surveyed the public and found that insurance fraud is commonplace, and committed by people of different classes— often unwittingly, and rarely with much regret. Insurance companies were surveyed, and data collected by interviews with insurance staff. It emerged that many insurers did not realise they had an insurance fraud problem, and those that did were either doing little to prevent it or were using ineffective methods. Insurance fraudsters are often given a great deal of help, often by officials who abuse the trust placed in them; insurers’ relationship with the police and with loss adjusters is not geared to stopping fraudsters, and insurance fraud is thus rendered easier. To illustrate this, and with the help of an insurance company, the researcher conducted a mock insurance fraud, and found it easy to commit. This study shows that insurance fraud is mostly an opportunistic crime. Within the study of crime prevention there is an approach which seeks to reduce the number of offences by curtailing the opportunities for crime. This is known as ‘situational crime prevention’, and is based on the ‘rational choice perspective’. Professor Ron Clarke, whose name is most closely associated with the approach, has called for more research to apply the principles and techniques of opportunity reduction to a range of crime types. This thesis represents an attempt to do this in relation to insurance fraud, and in so doing to stimulate ideas on how insurance fraud can be tackled effectively. In addition, it offers a new perspective on the situational approach and the techniques of opportunity reduction, plus a revised classification of these techniques. At the same time it offers a critique of the situational approach itself. The findings suggest that if fraud within the insurance industry is to be taken seriously then there are a range of structural concerns that need to be tackled, and that this moves beyond the scope of situational prevention.
9
Domingues, Rémi. "Machine Learning for Unsupervised Fraud Detection." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-181027.
Full textAbstract:
Fraud is a threat that most online service providers must address in the development of their systems to ensure an efficient security policy and the integrity of their revenue. Amadeus, a Global Distribution System providing a transaction platform for flight booking by travel agents, is targeted by fraud attempts that could lead to revenue losses and indemnifications. The objective of this thesis is to detect fraud attempts by applying machine learning algorithms to bookings represented by Passenger Name Record history. Due to the lack of labelled data, the current study presents a benchmark of unsupervised algorithms and aggregation methods. It also describes anomaly detection techniques which can be applied to self-organizing maps and hierarchical clustering. Considering the important amount of transactions per second processed by Amadeus back-ends, we eventually highlight potential bottlenecks and alternatives.
10
Jurgovsky, Johannes. "Context-aware credit card fraud detection." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI109.
Full textAbstract:
La fraude par carte de crédit est devenue un problème majeur dans le secteur des paiements électroniques. Dans cette thèse, nous étudions la détection de fraude basée sur les données transactionnelles et abordons plusieurs de ces défis complexes en utilisant des méthodes d'apprentissage automatique visant à identifier les transactions frauduleuses qui ont été émises illégitimement au nom du titulaire légitime de la carte. En particulier, nous explorons plusieurs moyens d’exploiter les informations contextuelles au-delà des attributs de base d’une transaction, notamment au niveau de la transaction, au niveau de la séquence et au niveau de l'utilisateur. Au niveau des transactions, nous cherchons à identifier les transactions frauduleuses qui présentent des caractéristiques distinctes des transactions authentiques. Nous avons mené une étude empirique de l’influence du déséquilibre des classes et des horizons de prévision sur la performance d d'un classifieur de type random forest. Nous augmentons les transactions avec des attributs supplémentaires extraits de sources de connaissances externes et montrons que des informations sur les pays et les événements du calendrier améliorent les performances de classification, particulièrement pour les transactions ayant lieu sur le Web. Au niveau de la séquence, nous cherchons à détecter les fraudes qui sont difficiles à identifier en elles-mêmes, mais particulières en ce qui concerne la séquence à court terme dans laquelle elles apparaissent. Nous utilisons un réseau de neurone récurrent (LSTM) pour modéliser la séquence de transactions. Nos résultats suggèrent que la modélisation basée sur des LSTM est une stratégie prometteuse pour caractériser des séquences de transactions ayant lieu en face à face, mais elle n’est pas adéquate pour les transactions ayant lieu sur le Web. Au niveau de l'utilisateur, nous travaillons sur une stratégie existante d'agrégation d'attributs et proposons un concept flexible nous permettant de calculer de nombreux attributs au moyen d'une syntaxe simple. Nous fournissons une implémentation basée sur CUDA pour pour accélerer le temps de calcul de deux ordres de grandeur. Notre étude de sélection des attributs révèle que les agrégats extraits de séquences de transactions des utilisateurs sont plus utiles que ceux extraits des séquences de marchands. De plus, nous découvrons plusieurs ensembles d'attributs candidats avec des performances équivalentes à celles des agrégats fabriqués manuellement tout en étant très différents en termes de structure. En ce qui concerne les travaux futurs, nous évoquons des méthodes d'apprentissage artificiel simples et transparentes pour la détection des fraudes par carte de crédit et nous esquissons une modélisation simple axée sur l'utilisateurCredit card fraud has emerged as major problem in the electronic payment sector. In this thesis, we study data-driven fraud detection and address several of its intricate challenges by means of machine learning methods with the goal to identify fraudulent transactions that have been issued illegitimately on behalf of the rightful card owner. In particular, we explore several means to leverage contextual information beyond a transaction's basic attributes on the transaction level, sequence level and user level. On the transaction level, we aim to identify fraudulent transactions which, in terms of their attribute values, are globally distinguishable from genuine transactions. We provide an empirical study of the influence of class imbalance and forecasting horizons on the classification performance of a random forest classifier. We augment transactions with additional features extracted from external knowledge sources and show that external information about countries and calendar events improves classification performance most noticeably on card-not-present transaction. On the sequence level, we aim to detect frauds that are inconspicuous in the background of all transactions but peculiar with respect to the short-term sequence they appear in. We use a Long Short-term Memory network (LSTM) for modeling the sequential succession of transactions. Our results suggest that LSTM-based modeling is a promising strategy for characterizing sequences of card-present transactions but it is not adequate for card-not-present transactions. On the user level, we elaborate on feature aggregations and propose a flexible concept allowing us define numerous features by means of a simple syntax. We provide a CUDA-based implementation for the computationally expensive extraction with a speed-up of two orders of magnitude. Our feature selection study reveals that aggregates extracted from users' transaction sequences are more useful than those extracted from merchant sequences. Moreover, we discover multiple sets of candidate features with equivalent performance as manually engineered aggregates while being vastly different in terms of their structure. Regarding future work, we motivate the usage of simple and transparent machine learning methods for credit card fraud detection and we sketch a simple user-focused modeling approach
11
Lu, Yifei. "Deep neural networks and fraud detection." Thesis, Uppsala universitet, Tillämpad matematik och statistik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-331833.
Full text
12
Aboutajdine, Reda. "Deterrence and learning effects in insurance fraud audits." Thesis, Institut polytechnique de Paris, 2019. http://www.theses.fr/2019IPPAX016.
Full textAbstract:
La fraude à l'assurance est une menace majeure pour les marchés assurantiels dont le traitement passe par la conception de politiques d’audit crédibles et ciblées. Cette thèse étudie les mécanismes de dissuasion et d’apprentissage dans l’audit de la fraude l’assurance, notamment quand des prestataires (garagistes, opticiens, etc.) jouent le rôle d'intermédiaires entre l'assureur et les assurés. Le premier chapitre est une étude empirique des effets dissuasifs de l’audit, fruit d’une collaboration avec IBM France et PRO BTP, dans le cadre du déploiement de la solution anti-fraude Solon. Cette analyse montre que les audits subis par un opticien ont pour effet de réduire sa fraude future. Plus spécifiquement, l’effet dissuasif est d’autant plus fort que la menace d’audit est crédible, soulignant l’importance de l’engagement dans la lutte contre la fraude. Les deuxième et troisième chapitres étudient un problème d’audit dynamique où l'information joue un rôle central. L’auditeur y interagit de façon répétée avec des prestataires non-stratèges et peut apprendre à propos de leur propension à frauder sur la base des résultats de l'audit. Le deuxième chapitre utilise un modèle à deux périodes pour mettre en évidence cet effet d’apprentissage, dont la conséquence est qu’il est optimal d’auditer plus intensément au début de la relation. Le troisième chapitre étend ce modèle à un nombre arbitraire ou infini de périodes, et montre que l’audit optimal est d’autant plus intense qu’il reste un nombre important d’interactions futures. L’intuition réside dans le fait que davantage d'audit au présent, quoique coûteux, a des répercussions informationnelles positives sur toutes les périodes suivantes. Enfin, le quatrième chapitre réunit les mécanismes de dissuasion et d’apprentissage dans un même modèle dynamique de réputation, avec des prestataires stratèges. Il montre l'existence d'une forme de dissuasion réputationnelle où l’apprentissage transforme la dissuasion en une menace intertemporelle. En d’autres termes, un prestataire sera davantage dissuadé dans le présent car il risque de détériorer sa réputation future s’il se fait attraper en train de frauderInsurance fraud is a serious threat to insurance markets and is tackled through the design of credible and targeted auditing policies. This thesis studies the deterrence and learning mechanisms of insurance fraud audits, especially when service providers (car repairers, opticians, etc.) act as intermediaries between the insurer and the policyholders. The first chapter is an empirical assessment of the deterrence effects of auditing. It was conducted in collaboration with IBM France and PRO BTP, in the context of the deployment of the Solon counter-fraud solution. This assessment shows that incurred audits decrease an optician’s subsequent fraud. More specifically, the more credible the audit threat, the stronger this deterrence effect, emphasizing the importance of commitment in counter-fraud efforts. The second and third chapters examine a dynamic auditing problem where information plays a central role. The auditor interacts repeatedly with non-strategic service providers and can learn about their propensity to defraud from the auditing outcomes. The second chapter relies on a two-period model to show the existence of this learning effect, whose consequence is that it is optimal to audit more at the beginning of the relationship. The third chapter extends this model to an arbitrary or infinite number of periods, and shows that the further away the time horizon, the larger the optimal auditing efforts. Intuition stems from the fact that more auditing in the present, though costly, has a positive informational impact on all future periods. Finally, the fourth chapter combines the deterrence and learning mechanisms in the same dynamic reputation model, with strategic service providers. It reveals a reputation-based deterrence effect, where learning turns deterrence into an intertemporal threat. In other words, a service provider will be deterred more strongly in the present because of the risk of seeing his future reputation deteriorate if he gets caught defrauding
13
Edmonds, Mark Allen. "THE INVISIBLE FRAUD: THE IMPACT OF INATTENTIONAL BLINDNESS ON AUDITOR FRAUD DETECTION." OpenSIUC, 2016. https://opensiuc.lib.siu.edu/dissertations/1153.
Full textAbstract:
Evidence gathered from major fraud investigations over the last decade has revealed that auditors in these cases failed to attend to fraud red flags within the substantive testing evidence. Research in psychology regarding inattentional blindness (IB) provides a theoretical framework for explaining why auditors may be prone to missing fraud red flags. This study examines the presence of IB during the performance of substantive testing and proposes two distinct interventions. Each intervention is predicted to improve auditor fraud detection. In a scenario involving fraudulent revenue transactions, findings show that a slight modification to the standard audit procedures significantly improves an auditor’s detection of red flags indicative of fraud. A second intervention involving the performance of a strategic reasoning task did not yield significant results. Overall, the results suggest that audit firms should consider making a cost effective adjustment to their standard audit program to improve fraud detection.
14
Yau, Kin-pong Harry. "The role of accountants in fraud detection." Click to view the E-thesis via HKUTO, 2000. http://sunzi.lib.hku.hk/hkuto/record/B42575552.
Full text
15
Rose, Lydia M. "Modernizing Check Fraud Detection with Machine Learning." Thesis, Utica College, 2018. http://pqdtopen.proquest.com/#viewpdf?dispub=13421455.
Full textAbstract:
Even as electronic payments and virtual currencies become more popular, checks are still the nearly ubiquitous form of payment for many situations in the United States such as payroll, purchasing a vehicle, paying rent, and hiring a contractor. Fraud has always plagued this form of payment, and this research aimed to capture the scope of this 15th century problem in the 21st century. Today, counterfeit checks originating from overseas are the scourge of online dating sites, classifieds forums, and mailboxes throughout the country. Additional frauds including alteration, theft, and check kiting also exploit checks. Check fraud is causing hundreds of millions in estimated losses to both financial institutions and consumers annually, and the problem is growing. Fraud investigators and financial institutions must be better educated and armed to successfully combat it. This research study collected information on the history of checks, forms of check fraud, victimization, and methods for check fraud prevention and detection. Check fraud is not only a financial issue, but also a social one. Uneducated and otherwise vulnerable consumers are particularly targeted by scammers exploiting this form of fraud. Racial minorities, elderly, mentally ill, and those living in poverty are disproportionately affected by fraud victimization. Financial institutions struggle to strike a balance between educating customers, complying with regulations, and tailoring alerts that are both valuable and fast. Applications of artificial intelligence including machine learning and computer vision have many recent advancements, but financial institution anti-fraud measures have not kept pace. This research concludes that the onus rests on financial institutions to take a modern approach to check fraud, incorporating machine learning into real-time reviews, to adequately protect victims.
16
Westerlund, Fredrik. "CREDIT CARD FRAUD DETECTION (Machine learning algorithms)." Thesis, Umeå universitet, Statistik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-136031.
Full textAbstract:
Credit card fraud is a field with perpetrators performing illegal actions that may affect other individuals or companies negatively. For instance, a criminalcan steal credit card information from an account holder and then conduct fraudulent transactions. The activities are a potential contributory factor to how illegal organizations such as terrorists and drug traffickers support themselves financially. Within the machine learning area, there are several methods that possess the ability to detect credit card fraud transactions; supervised learning and unsupervised learning algorithms. This essay investigates the supervised approach, where two algorithms (Hellinger Distance Decision Tree (HDDT) and Random Forest) are evaluated on a real life dataset of 284,807 transactions. Under those circumstances, the main purpose is to develop a “well-functioning” model with a reasonable capacity to categorize transactions as fraudulent or legit. As the data is heavily unbalanced, reducing the false-positive rate is also an important part when conducting research in the chosen area. In conclusion, evaluated algorithms present a fairly similar outcome, where both models have the capability to distinguish the classes from each other. However, the Random Forest approach has a better performance than HDDT in all measures of interest.
17
Perols, Johan L. "Detecting Financial Statement Fraud: Three Essays on Fraud Predictors, Multi-Classifier Combination and Fraud Detection Using Data Mining." [Tampa, Fla] : University of South Florida, 2008. http://purl.fcla.edu/usf/dc/et/SFE0002486.
Full text
18
Richards, Katie. "Fraud unravels all? : a critical examination of the fraud rules in marine insurance and documentary credit transactions." Thesis, Cardiff University, 2017. http://orca.cf.ac.uk/110284/.
Full textAbstract:
This thesis considers the extent to which ‘fraud unravels all’ explains the judicial response to fraudulent marine insurance claims and fraud in documentary credit transactions. The simplicity of the maxim suggests that fraud does not unduly trouble the courts and gives the impression of a uniform and deterrent approach to fraud within the civil law. The comparison made in this thesis demonstrates this impression to be misleading; the courts have conceived of fraud differently and have employed context-specific policy concerns to justify the shape of each fraud rule. The insurance discussions are dominated by deterrence with legal sanctions placed at the heart of the model. By contrast, the trade finance courts adopt a more laissez-faire attitude which prioritises the efficiency of the credit mechanism and considers deterrence an ex ante issue for the parties. Accordingly, this thesis examines the respective policy justifications and considers their continued validity in light of comparative and empirical evidence. In the insurance context, it is argued that the judicial understanding of deterrence is outdated which renders the resulting legal rule ineffective. An examination of approaches to fraud in other jurisdictions then demonstrates the possibility of constructing a more nuanced remedial framework which would balance the competing policy considerations of deterrence and proportionality. The documentary credit discussion contends that the narrow English approach to fraud is not an inevitable policy decision and moreover, has resulted in detrimental consequences for the credit mechanism. It employs empirical data to develop an explanation of deterrence for the duration of credit transactions. In both contexts, these arguments have important implications for the future development of the law. In summary, this research undermines the utility of ‘fraud unravels all’ and calls instead for courts and academics to resist instinctively attractive solutions in favour of a robust, empirically-informed approach to fraud.
19
Zhou, Zhihong. "Applying manufacturing batch techniques to customer fraud detection /." View abstract or full-text, 2004. http://library.ust.hk/cgi/db/thesis.pl?IEEM%202004%20ZHOU.
Full textAbstract:
Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2004.Includes bibliographical references (leaves 39-42). Also available in electronic version. Access restricted to campus users.
20
Schillermann, Marcia. "Early Detection and Prevention of Corporate Financial Fraud." ScholarWorks, 2018. https://scholarworks.waldenu.edu/dissertations/6117.
Full textAbstract:
The economic cost of financial statement fraud continues to be a problem for organizations and society. The research problem addressed in this study was the limited risk management strategies available for the early detection and prevention of financial statement fraud by corporate managers and auditors. These strategies are important to the proactive prevention of fraud. This study is important to future trustworthiness of financial statements. The purpose of this qualitative, multiple-case study was to explore current early detection and prevention methods in financial statement fraud using a risk management conceptual framework. The research question focused on current fraud detection and prevention policies and risk management strategies that are currently used for proactively detecting and preventing financial statement fraud. Multiple sources of information were used, including examining recent financial fraud scandals, interviews, documents, and past research. The target population was managers and auditors of publicly traded corporations. A purposive sampling procedure was used to select 23 participants, which provided rich data. The qualitative data was coded and analyzed using the concept of risk management, along with triangulation to ensure credibility. The key findings indicated that current practitioners are moving beyond the era of reactive measures born from the past fraud crises and are working toward improved financial statement quality and trust. The results of the study also indicated that future research should include proactive methods of preventing fraud. This study is socially significant because it could enhance the ability to trust financial statement reporting in the future and improve corporate reputations.
21
Amaya, de la Pena Ignacio. "Fraud detection in online payments using Spark ML." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-219916.
Full textAbstract:
Frauds in online payments cause billions of dollars in losses every year. To reduce them, traditional fraud detection systems can be enhanced with the latest advances in machine learning, which usually require distributed computing frameworks to handle the big size of the available data. Previous academic work has failed to address fraud detection in real-world environments. To fill this gap, this thesis focuses on building a fraud detection classifier on Spark ML using real-world payment data. Class imbalance and non-stationarity reduced the performance of our models, so experiments to tackle those problems were performed. Our best results were achieved by applying undersampling and oversampling on the training data to reduce the class imbalance. Updating the model regularly to use the latest data also helped diminishing the negative effects of non-stationarity. A final machine learning model that leverages all our findings has been deployed at Qliro, an important online payments provider in the Nordics. This model periodically sends suspicious purchase orders for review to fraud investigators, enabling them to catch frauds that were missed before.Bedrägerier vid online-betalningar medför stora förluster, så företag bygger bedrägeribekämpningssystem för att förhindra dem. I denna avhandling studerar vi hur maskininlärning kan tillämpas för att förbättra dessa system. Tidigare studier har misslyckats med att hantera bedrägeribekämpning med verklig data, ett problem som kräver distribuerade beräkningsramverk för att hantera den stora datamängden. För att lösa det har vi använt betalningsdata från industrin för att bygga en klassificator för bedrägeridetektering via Spark ML. Obalanserade klasser och icke-stationäritet minskade träffsäkerheten hos våra modeller, så experiment för att hantera dessa problem har utförts. Våra bästa resultat erhålls genom att kombinera undersampling och oversampling på träningsdata. Att använda bara den senaste datan och kombinera flera modeller som ej har tränats med samma data förbättrar också träffsäkerheten. En slutgiltig modell har implementerats hos Qliro, en stor leverantör av online betalningar i Norden, vilket har förbättrat deras bedrägeribekämpningssystem och hjälper utredare att upptäcka bedrägerier som tidigare missades.
22
Dal, Pozzolo Andrea. "Adaptive Machine Learning for Credit Card Fraud Detection." Doctoral thesis, Universite Libre de Bruxelles, 2015. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/221654.
Full textAbstract:
Billions of dollars of loss are caused every year by fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to the non-stationary distribution of the data, the highly unbalanced classes distributions and the availability of few transactions labeled by fraud investigators. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about what is the best strategy. In this thesis we aim to provide some answers by focusing on crucial issues such as: i) why and how undersampling is useful in the presence of class imbalance (i.e. frauds are a small percentage of the transactions), ii) how to deal with unbalanced and evolving data streams (non-stationarity due to fraud evolution and change of spending behavior), iii) how to assess performances in a way which is relevant for detection and iv) how to use feedbacks provided by investigators on the fraud alerts generated. Finally, we design and assess a prototype of a Fraud Detection System able to meet real-world working conditions and that is able to integrate investigators’ feedback to generate accurate alerts.Doctorat en Sciences
info:eu-repo/semantics/nonPublished
23
Ponce, Michael. "Healthcare fraud and non-fraud healthcare crimes: A comparison." CSUSB ScholarWorks, 2007. https://scholarworks.lib.csusb.edu/etd-project/3233.
Full textAbstract:
Healthcare fraud is a major problem within the healthcare industry. The study examined medical fraud, its laws, and punishments on federal and state levels. It compared medical fraud to non-fraud crimes done in the healthcare industry. This comparison will be done on a state level. The study attempted to analyze the severity of fraud against non-fraud and that doctors would commit fraud offenses more often than non-fraud offenses.
24
Bergman, Bengt. "E-fraud E-fraud, state of the art and counter measures." Thesis, Linköping University, Department of Computer and Information Science, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-2798.
Full textAbstract:
This thesis investigates fraud and the situation on Internet with e-commerce today, to point on some potential threats and needed countermeasures. The work reviews several state of the art e-fraud schemes, techniques used in the schemes and statistics on the extent of e-fraud. This part shows that e-frauds are today both sophisticated and widespread.
Since real world frauds are deemed impossible to fully cover in order to predict potential new e-frauds, the thesis adopts a different approach. It suggests two abstraction models for fraud cases, a protocol model and a functional model. These are used to perform analysis on case studies on both telecom frauds and e-frauds. The analysis presents characteristics for both types of frauds. Using one of the abstraction models, the functional model, conceptually similar cases among telecom frauds as well as e-fraud cases are identified. The similar cases in each category are then compared, using the other abstraction model, the protocol model. The study shows that concepts from telecom frauds already exist in e-frauds.
Several challenges and some possibilities in e-fraud prevention and detection are also extracted in the comparative study of the different categories. The major consequence of the challenges is e-frauds’ higher scalability compared to telecom frauds.
Finally, this thesis covers several existing countermeasures in e-commerce along with specific countermeasures against auction fraud, phishing and spam. However, it is shown that these countermeasures do not address the challenges in e-fraud prevention and detection to a satisfactory extent. Therefore, this thesis proposes several high-level countermeasures in order to address the challenges.
25
Mohamed, Mudzamir. "Countering fraud in the insurance industry : a case study of Malaysia." Thesis, University of Portsmouth, 2013. https://researchportal.port.ac.uk/portal/en/theses/countering-fraud-in-the-insurance-industry(3959e2cd-403b-4a18-86f7-99e89948ee19).html.
Full textAbstract:
Insurance fraud is noted as one of the most significant challenges to the financial stability of the insurance market (Wells, 2011; Yusuf & Babalola, 2009). The main purpose of this study is to explore and access the magnitude of the issues in a company setting and gather responses from the general environment regarding this threat. Due to the Malaysian cultural set up, there are gaps of research in this topic as fraud issues are considered sensitive and taboo. Although some researchers have shed some light on issues pertaining to fraud in Malaysia, however these studies have focused purely on mitigation and countering in the economic dimension without making relationship with authorities concerned. This study looks to support the idea of Malaysia‘s current Prime Minister, Dato Mohd Najib Tun Razak, which are encompassed in the 'Economic Transformation Plan'. During the start of his Prime Minister role he urged all sectors to be more transparent and responsive. Besides, the pattern of an economic downturn for a second wave in 2008 demanded the insurers to offer fewer products or services, and at the same time be more stringent on the policy inclusions (Bank Negara Malaysia (BNM), 2010). This research has examined a broad volume of articles from specific areas of fraud including cases of insurance fraud. This is done to grasp the fraud control strategies and the current trends in Malaysia. This research applies multiple research methods that comprise of interviews', observations and document inspections within the selected companies. This to facilitate the coherence and collaborative work of the authorities selected in the case study which are crucial in evaluating the process of countering fraud. In order to ensure the success of this study, it utilized and adopted the CIPFA Red Book 2 as the main benchmark to gauge the initiatives of countering fraud in the Malaysian insurance industry. The findings of the study revealed that there are two companies integrating good initiatives which enable them to avoid insurance fraud cases to a greater extent. However, one of the companies did not address the issues entirely as the operation of the working environment is atypical. All professionals agreed upon that this task, countering fraud and corruption, demands a certain set of skills. By that, this advocates the idea that countering fraud initiatives are not for a single performer imposition only. On the contrasting side, due to the hierarchy and supremacy in Malaysia, Bank Negara Malaysia (BNM) plays a vital role in the insurance market. However, they are still unwilling in making these concerns part of the national agenda since many companies have only recorded a satisfactory level in integrating the functions of combating fraud. However, specialists have urged some officials and relevant authorities, insurers and professionals in making precise arrangements to embark on the issues in an appropriate process.
26
Aborbie, Solomon. "Narrowing the Gap of Financial Fraud Detection in Corporations." Thesis, Walden University, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=3688003.
Full textAbstract:
Business leaders remain exposed to financial and accounting fraud as well as loss of profitability, despite the dictates of the SOX Act of 2002. The most challenging aspect of corporate management is the unexpected nature of an emerging, existing, or an inherent financial risk. Guided by the evolution of fraud theory, this exploratory case study's purpose was to identify and explore the financial management strategies that corporate financial managers need to adequately protect investors. Twenty participants from a population group of corporate auditors of Fortune 1000 corporations within 70 miles of Columbus, Ohio provided input for this study. Data from the interviews were analyzed through coding, reviewing, categorizing, and combining common statements. The research findings included themes of knowledge and types of risks; the impact of financial fraud and risks on investment; the impact of accounting, auditing, and financial reporting standards; as well as financial management training to minimize audit expectations. These themes formed the focus of exploring the financial management strategies that corporate financial managers need to adequately protect investors and investments. In addition to the antifraud measures, financial managers may detect and control inherent risks in emerging opportunities for positive social change that includes enhanced knowledge in diversification of investments, an increase in economic resources, economic growth, and greater employment in the United States.
27
Poissant, Mathieu. "Statistical methods for insurance fraud detection." Thèse, 2008. http://hdl.handle.net/1866/8191.
Full text
28
Garcia, Nuno Ricardo da Cruz. "Social Network Analysis for Insurance Fraud Detection." Master's thesis, 2015. http://hdl.handle.net/10400.6/5895.
Full textAbstract:
Fraud detection configures a very interesting problem yet to solve, particularly when related to
automobile insurance claims. In this research we address this challenge from a not so typical
"record" perspective of data, but rather from a network point of view, where relations between
entities involved in claims are explored to detect organized fraud structures.
First we propose a random data generator, able to generate graphs that resemble realistic patterns
evidenced on authentic scenarios, based on insurance authorities statistics and graph features
already described in the literature. We show how this graph copes with the requirements on
every single step, and how it can be adjustable to different locals.
Secondly, we propose a variation of Subelj approach [ŠFB11], and apply it to the generated graphs.
This approach explores the relations between entities, takes advantage of the power of social
network analysis metrics and statistical methods such as RIDIT scores and Principal Component
Analysis to score each connected component and Support Vector Machines to classify them either
fraudulent or honest.
The main contributions of this research is a new approach to generate data regarding automobile
insurance claims suitable for social network analysis, and a variation of an approach described
on the literature, proving thus not only benchmark results but also new insights regarding fraud
detection through graph-based algorithms.A detecção de fraude configura um desafio interessante, que não está totalmente resolvido particularmente no que respeita a fraude em seguros automóvel. A fraude no seguro automóvel representa várias centenas de milhões de euros de prejuízo para as companhias seguradoras na Europa, e consequentemente um aumento de preço das apólices cobrado ao consumidor final. A dimensão do mercado segurador e o impacto que a fraude tem nas companhias faz com que a tarefa de detecção de fraude possa transformada em vantagem competitiva, e assim se assuma como uma prioridade no sector. A fraude que provoca danos mais volumosos é a praticada por grupos organizados, que concebem esquemas e contornam o sistema de forma a sistematicamente repetir a actividade fraudulenta. Esta dissertação aborda o tema da detecção de fraude de uma perpectiva que não será a mais comum nos sistemas hoje em dia utilizados. Em vez de analisar dados de sinistros como números e estatísticas isoladas, tenta perceber as relações entre as entidades que participam nos sinistros e identificar estruturas suspeitas de entre um vasto conjunto de dados. O conjunto de dados necessário à análise que propomos tem características especiais, como por exemplo ser sensível a divulgação a terceiros por conter dados pessoais e ser normalmente propriedade das companhias de seguros ou de estruturas policiais. Por estes motivos, não existem conjuntos de dados públicos que permitam o desenvolvimento de uma investigação neste sentido. Para colmatar este facto, propomos um gerador de grafos aleatório capaz de produzir redes com padrões semelhantes àqueles que seria expectável encontrar em cenários reais. O gerador incorpora conhecimento descrito na literatura [ŠFB11] sobre características e padrões encontrados em conjuntos de dados relacionados com este tema. Além disso, especialistas de seguros da Deloitte, parceira no desenvolvimento desta dissertação, contribuiram com a sua experiência no campo para que o gerador pudesse representar fielmente a realidade. No que respeita à detecção de fraude, este trabalho propõe uma abordagem que inclui a classificação de componentes do grafo como fraudulentos ou honestos, através do uso do conhecido classificador SVM (Support Vector Machine). São feitas avaliações de performance com várias variações do método proposto e de parte do método que inspirou a abordagem usada, chamado PRIDIT. Uma das conclusões mais interessantes que estas experiências parecem sugerir é que nem sempre o uso do método PRIDIT garante o aumento de performance desejado. As contribuições deste trabalho centram-se no desenvlvimento de um gerador de grafos para o contexto de análise de fraude de seguros automóvel, e na avaliação e comparação do uso de SVM na classificação de componentes fraudulentos.
29
Ai, Jing 1981. "Supervised and unsupervised PRIDIT for active insurance fraud detection." 2008. http://hdl.handle.net/2152/17724.
Full textAbstract:
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
30
Mouco, João Marques Paredes. "Insurance Fraud Detection - Using Complex Networks to Detect Suspicious Entity Relationships." Master's thesis, 2019. http://hdl.handle.net/10362/93423.
Full textAbstract:
The insurance industry is undoubtedly one of the main drivers of today’s
economy and certainly will be so for the foreseeable future. This is derived from
a basic need every person has, and that is to have financial and personal safety.
Despite all this, some entities try to induce fraud on their policies or to circumvent
some legal mechanics, to gain unlawful benefits and advantages. This
being said, insurance fraud constitutes a grave downside to insurance companies
as it directly translates to a loss of economical assets as well as the opportunity to
establish a precursor to further exploitation of the system in place.
In this context, this dissertation proposes a framework to help detect the most
common types of insurance fraud and scam. Most of the times, insurance scams
are usually detected after they took place, this means the companies are already
at a loss when they detect it. This framework, which is based upon complex networks
for relationship visualization, takes into consideration the relationships
already in place between the different entities of the insurance hub-world, advises
the responsible entities for fraud prosecution on suspicious relationships.
This way, frauds and scams can be detected early on, thus minimizing the losses
associated.
This dissertation is being supported by at Holos, S.A using the online insurance
management tool, also known as RIFT. This tool gathers data from actual
insurance companies, giving the study a higher degree of veracity and applicability
in the real world.
31
Moreno, María Fernanda Osorio. "Comparing the performance of oversampling techniques for imbalanced learning in insurance fraud detection." Master's thesis, 2018. http://hdl.handle.net/10362/33863.
Full textAbstract:
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced AnalyticsAlthough the current trend of data production is focused on generating tons of it every second, there are situations where the target category is represented extremely unequally, giving rise to imbalanced datasets, analyzing them correctly can lead to relevant decisions that produces appropriate business strategies. Fraud modeling is one example of this situation: it is expected less fraudulent transactions than reliable ones, predict them could be crucial for improving decisions and processes in a company. However, class imbalance produces a negative effect on traditional techniques in dealing with this problem, a lot of techniques have been proposed and oversampling is one of them. This work analyses the behavior of different oversampling techniques such as Random oversampling, SOMO and SMOTE, through different classifiers and evaluation metrics. The exercise is done with real data from an insurance company in Colombia predicting fraudulent claims for its compulsory auto product. Conclusions of this research demonstrate the advantages of using oversampling for imbalance circumstances but also the importance of comparing different evaluation metrics and classifiers to obtain accurate appropriate conclusions and comparable results.
32
Guimaraes, Amanda De Azevedo. "Digital transformation in the insurance industry: applications of artificial intelligence in fraud detection." Master's thesis, 2020. http://hdl.handle.net/10362/108422.
Full textAbstract:
The insurance industry has always been a crucial part of the economy and society’s progress worldwide. However, it is currently facing an unprecedented scenario composed of high risks and opportunities. This study aims to explain and analyze the process of digitalization in this sector and what are the available applications of artificial intelligence for fraud detection in claim management.It also comprehends a discussion about Brazil, with recommendations that were validated with local professionals from major players in the industry. Hence, the methodological approach chosen for this study wasa combination of the qualitative method, essentially based on the review and analysis of academic literature and reports, with important interviews.Lastly, it was concluded that most insurance companies are still at the beginning of the digitalization process, seeking a better understanding of its landscape. Consequently, A.I.applications are slowly being implemented by some large insurance companies.
33
Oliveira, Inês Bruno de. "Application of neural networks to the detection of fraud in workers’ compensation insurance : application to a Portuguese insurer." Master's thesis, 2018. http://hdl.handle.net/10362/32561.
Full textAbstract:
Project Work presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Risk Analysis and ManagementInsurance relies on a complex trust-based relationship in which a policyholder pays in advance to be protected in the future. In Portugal, workers’ compensation insurance is mandatory which may restrict the course of action of both players. Insurers face significant losses, not only due to its core business, but also due to the swindles of claimants and policyholders. Insureds may not have in the market what they really want to acquire which may encourage fraudulent actions. Traditional fraud detection methods are no longer adequately protecting institutions in a world with increasingly sophisticated fraud techniques. This work focuses on creating an artificial neural network which will learn with insurance data and evolve continuously over time, anticipating fraudulent behaviours or actors, and contribute to institutions risk protection strategies.
34
LIU, SHUN-CHUNG, and 劉順鐘. "The Research of Blockchain in Detecting and Preventing of Insurance Fraud." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/v9f966.
Full textAbstract:
碩士國立臺北科技大學
管理學院資訊與財金管理EMBA專班
105
“Fintech” is one of the most important innovation and evolution for financial industry in one hundred year. Blockchain technology originated from Bitcoin is the most disruptive among them. It will change the gaming rules of financial industry or even other industries. Blockchain is an innovative “Distributed Ledger Technology” which provides a trust, unmodifiable, transparent, rapid and secure ledger system in a decentralized organization. Insurance fraud causes tremendous loss in every country. In Taiwan, the estimated loss of insurance fraud is around NT$ 150 billion per year, which means that each family pays extra NT$ 18,900 for insurance premium per year. In Taiwan, the insurance fraud detection and prevention currently rely on a “Reporting System” which is implemented and maintained by Life Insurance Association. All Insurance companies are mandatory to report all insurance polices they’ve sold upon accepting and underwriting the insurance policies. However, this system is a centralized system without trenchancy. The whole reporting process is not efficient enough to prevent insurance fraud. The research objective of this paper is to design an “Insurance Blockchain System” which can replace “Reporting System”. The “Insurance Blockchain System” will be able to transparently and immediately record all the insurance transactions (activities) into a distributed Insurance ledger using Blockchain technology. This system will make an App called “i-wallet” for customers and build “Distributed Insurance Ledger” to record all insurance activities including applications and claiming. It will generate so called “Personal Insurance Balance” and “Reputation System”. All insurance records are transparent, real-time and unmodifiable. It will create leading indicators to improve the detection and prevention of insurance fraud.
35
Ko, Ya-Ling, and 柯雅玲. "A Study on Insurance Fraud." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/79ar45.
Full textAbstract:
碩士國立臺灣大學
科際整合法律學研究所
105
With the increasing dependence of the modern society on the insurance system, the stability of the insurance system is very important for the individual, the family, and the society. Every country is committed to the prevention of insurance fraud because it not only damages the stability of the insurance system but also is accompanied by criminal offences frequently. In 2008 and 2015, Japan and the United Kingdom enacted new insurance law including special provisions to solve insurance fraud. However, Taiwan has not yet enacted provisions like those. To begin with, this paper will introduce the current situation of anti-insurance fraud in Taiwan from these three aspects: legislative level, administrative level and the insurance industry. Then, this paper will introduce the Japanese and British insurance law relates to anti-insurance fraud. Furthermore, can the insurer terminate the contract when the policyholder, the insured, or the beneficiary commits insurance fraud if there are such terms in the insurance policy? Finally, this paper will draw some conclusions and give some advice. It is hoped that the discussion in this article will serve as a reference for future amendments to the relevant law.
36
CHANG, KAI-JAY, and 張凱傑. "The Life Insurance Agents' Attitudes toward Customer Insurance Fraud." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/7hf8p7.
Full textAbstract:
碩士逢甲大學
風險管理與保險學系
106
With higher education standard, people realize that insurance not only compensate loss to danger but also stable development of economy. Compare to past, the willing of buying insurance is higher, so is insurance fraud. Insurance fraud obviously violates the meaning of insurance, increases social cost and causes higher rate so that getting insurance is more difficult to people. This study is based on salesperson and fraud by taking former researches as references. By making questionnaire to Taiwan insurance salespersons and recycling result for data quantify, we understand the attitude toward the customer when fraud happens. Through these data, we subjectively analyze the result and give our point of view for future study.
37
Pan, Wen-Chung, and 潘穩中. "Insurance Fraud Prevention from the Perspective of Insurance Law." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/89904647949592029943.
Full textAbstract:
碩士國立臺灣大學
法律學研究所
101
Insurance fraud which occurs frequently has been tackled by insurance practice and related regulations. With more observation, they put more efforts to establish the preventive norms, especially on the fraudulent claim after the occurrence of insurance accident. However, there are varieties of insurance fraud which is not limited to the cases mentioned above. Besides, according to Article 29 Section2 at Insurance Law, the insurance contract can survive even though the fraud done by the insured wrecks a havoc on the reliance between the insurer and insured, needless to say the insurer is able to terminate the contract by Insurance Law. Taiwan Insurance Law contains myriads of disadvantages. In lieu of these, it is suggested to adopt with some rule such as clausula rebus sic stantibus, the rule of continuous contract in civil law and regulations on special provisions in Insurance Law. Albeit, there are still insufficient to handle all problems. As to clausula rebus sic stantibus, the conditions of the rule is not so concrete and full of limitation to fulfill its purpose. Take the rule of continuous contract for another example, judges would be reluctant to utilize it because of lack of accurate regulations. Even though we put more hopes on special provisions in Insurance Law, it is still limited to Article 54-1and eventually becomes unavailable on solutions. With the perception of these problems, there is the tremendous amendment in Japanese Insurance Law in 2008, including the addition on fundamental termination regulation to provides with more concrete and instructive solutions to insurance fraud. In a nutshell, the thesis try to provides with legislative suggestion and proposes some drafts with the introduction these development to Taiwan Insurance Law .
38
Chen, Po-Wen, and 陳泊文. "The Research of Life Insurance Fraud." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/15865041529594434006.
Full textAbstract:
碩士淡江大學
保險學系保險經營碩士在職專班
98
Abstract: Deceptions of medical insurance claim on medical treatments have caused severe problems for the insurance industry and the social welfare system of National Health Insurance. Criminal cases triggered by insurance frauds also have negative influences on the public and the society. If problems of fraud claims of the like cannot be controlled, the society and economics will be facing with more strikes. By collecting a variety of insurance fraud cases and analyzing statistic data, this thesis expects to reveal characteristics of insurance fraud, behavior patterns, and criminal behaviors. By interviewing insurance specialists, this thesis also conducts a comparative study with reference to foreign cases in prevention or reduction of insurance frauds. In such, instruments are provided here to deal with insurance fraud cases in Taiwan in the near future. This study intends to provide life insurance enterprises, competent authorities, and National Health Insurance respectively with suggestions against insurance frauds. Three fields of suggestions are listed as follows: 1 Suggestions to Insurance Enterprises: 1.1 Control new business underwriting 1.2 Enhance professional knowledge of claim specialists and underwriters 1.3 Establish business quality and agency management 1.4 Evaluate insurance product property 2 Suggestions to Competent Authorities: 2.1 Promulgate and enact laws for insurance fraud 2.2 Establish special courts and investigation bureaus for insurance fraud 2.3 Amend related insurance regulations 2.4 Grant investigation power to insurance enterprises 2.5 Reinforce functionality of The Insurance Anti-fraud Institute (IAFI) 3 Suggestions to the Bureau of National Health Insurance 3.1 Enhance the information sharing system with insurance enterprises 3.2 Enhance internal control and audit functions
39
CHEN, PO-TSANG, and 陳伯滄. "On Insurance Fraud and Preventive Measures." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/zb7h82.
Full textAbstract:
碩士東吳大學
法律學系
106
Insurance is a kind of usage of principle in separated risks and sharing damages.It is done by numbers of people through sharing with this risks which are put on some people. Taiwan Insurance Institute estimates that insurance companies in Taiwan have to pay about 10 percent of insurance claim for the fraud,the total amount each year about 30 billion NT dollars.This is a big black hole for the insurance companies.Without making a proper prevention project,it will be the serious damage for the bona fide third party’s rights and benefits.The victims of insurance fraud are not only the insurer who pays the insurance bebefits but also the insured whose rights and privileges are supposed to be protected.This article is an attempt to provide an analysis on different types of insurance fraud and thereby assess the adequacy of the legal rules in governing insurance frauds and give recommendations for reducing the possibility of insurance frauds. The objective of this study is described as follows: First, exploring the type of crime of insurance fraud based on relevant judgment data in Taiwan. Second, exploring the Causes, Motives and Process of Insurance Fraud. Third, according to the research results, the countermeasures against the fraud of insurance are put forward for the reference of criminal investigation and drafting prevention policy of relevant units. The artile is based on theoretical analysis, comparative method and induction method with relevant legal rules of other countries taken for comparison and reference with an attempt to establish the methods for the prevention of insurance fraud.With the analysis of this article,preventative works against insurance fraud may be achieved through practical work.In addition,the inapplicability of laws of the erroneous applicable of law may be avoided,and supplying the insurance fraud models to the investigators and police officers kept fraud offenders from the crimes and positively decreased the social and people’s damages.Its goal was to achieve the insurance companies to lower their running business risks. Keywords：insurance fraud，insurane companies，insurane claim，prevention of insurance fraud.
40
Huang, Chih-Chin, and 黃智欽. "The Study on Personal Insurance Fraud." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/78125508519200524111.
Full textAbstract:
碩士淡江大學
保險學系保險經營碩士在職專班
103
Insurance fraud is the use of criminal methods to deceive insurance company in believing the occurrence of accident or lost, etc. for the intention of obtaining insurance claims. In earlier years because the occurrence of insurance fraud is not frequent, insurance companies and the general public did not pay much attention. Until recently years insurance fraud cases have increased drastically and repeatedly, thus catches public attentions. The continuous increases in insurance fraud cases have resulted in serious detrimental effects on insurance system and function. In present countries worldwide have legislation on insurance related fraud. The insurance law in Taiwan, although being through several major modifications, there has not yet any precise legislation regarding insurance fraud. With the continuous renewal of crime committing methods, fraud criminals also make use of the loophole of insurance law to commit crime. Thus, the study aims to explore motives of relative questions on insurance fraud. 表單編號：ATRX-Q03-001-FM031-01
41
Sun, Teng-Min, and 孫騰敏. "The Research of Automobile Insurance Fraud." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/55315347381202672962.
Full textAbstract:
碩士淡江大學
保險學系保險經營碩士在職專班
96
Automobile insurance fraud is an issue that has fallen on deaf ears in Taiwan’s insurance market and there is no sufficient statistics for reference. In fact, the insurance fraud is common in our insurance industry. In life insurance market, the breach of disclosure and the double insurance dispute are often involved in moral hazard. Furthermore, the abnormal losses are also found in the non-life insurance industry, especially in the marine cargo insurance, the fire insurance and the automobile insurance. This situation which leads loss ratio much higher than normal can not be neglected. Insurance fraud makes high profit especially when the economy goes to depression. The rapid growth of Insurance Fraud could be a threat to an insurance company. Thus, this research, 「The Research of Automobile Insurance Fraud」 divides the automobile insurance fraud into two major parts, one is underwriting and the other is claim. There are 20 types of automobile fraud. The top 3 causes are applying for insurance after loss on underwriting side, making up an insurance loss and making fake insurance accidents on claim side. In order to identify, avoid and prevent the insurance fraud for insurance companies, consumers, government and other related parties, there are 4 conclusions in this research. The first is to understand and analyze the types of insurance fraud. The second is to enhance the professional training for insurance employees. The third is to conduct internal auditing. The last is to enforce legal guidance for cooperating shops and related parties. This research concludes two ideas that could be provided to the non-life insurance operation. The first idea is to make anti insurance fraud law into practice. The contents are to enforce the function of the insurance anti-fraud institute of the R.O.C., to establish the dynamic tracking system of the insurance fraud, to set up the special telephone line for informing the crime and rewards, to amend related laws, to set up anti insurance fraud policy unit, to establish the network among the insurance industry, the medical industry, and the police, to educate more on insurance. The second idea is more cooperation to the insurance industry, including professional anti-fraud training, anti insurance fraud reporting system, insurance product design enforcement, international market linking, and social responsibility.
42
HUNG, CHIEN-WEN, and 洪健文. "Research of Insurance Crime-Focusing on National Health Insurance Fraud." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/892fuj.
Full text
43
Pienaar, Abel Jacobus. "Fraud detection using data mining." Thesis, 2014. http://hdl.handle.net/10210/9112.
Full textAbstract:
M.Com. (Computer Auditing)Fraud is a major problem in South Africa and the world and organisations lose millions each year to fraud not being detected. Organisations can deal with the fraud that is known to them, but undetected fraud is a problem. There is a need for management, external- and internal auditors to detect fraud within an organisation. There is a further need for an integrated fraud detection model to assist managers and auditors to detect fraud. A literature study was done of authoritative textbooks and other literature on fraud detection and data mining, including the Knowledge Discovery Process in databases and a model was developed that will assist the manager and auditor to detect fraud in an organisation by using a technology called data mining which makes the process of fraud detection more efficient and effective.
44
張志崧. "Fraud detection in telecom industry." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/13310978453851340438.
Full text
45
Wei, Ya-Hsun, and 魏雅珣. "A study on the Personal Insurance Fraud." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/bxmu25.
Full textAbstract:
碩士朝陽科技大學
保險金融管理系
105
The economic boom in Taiwan and the idea of having insurance is generally accepted bypublic. Nowadays insurance has become the necessity of commercial product.This is due to the increased number of insurance frauds which means the insurer or beneficiary would pay for the higher premium with the intent to obtain a fraudulent outcome by creating accidents on propose or even severe event, such as murder.This study explores how to reduce this situation by explaining the meaning, legal nature and national legislation of the insurance fraud, and then puts forward some suggestions on the existing Taiwan Insurance Law. Thisstudy is based on document analysis and case study method.It would analyse the root causes, such as, the reasons of why the events were taken place and features, from each case. The study is concerned the cases which are related to personal insurance fraud from 2011 to 2016 and the decisions were made by nationwide courtyards at the first trial. Suggestions and comments about how to avoid the fraud can be raised via reviewing and verifying the actual cases of insurance fraud. Therefore, we may reduce the number of insurance fraud. Finally, the study will list implementable suggestions based on the search result in order to reduce the incidence of insurance fraud in future.
46
Liao, Yi-Wen, and 廖怡雯. "The Study on Personal Injury Insurance Fraud." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/c3d9a3.
Full textAbstract:
碩士淡江大學
保險學系保險經營碩士在職專班
106
This study aims to investigate the bodily injury fraud in insurance. As insurance fraud becomes more serious, the number of cases escalates and the modus operandi becomes organized and professionalized, causing many horrifying and serious criminal cases that shake social perceptions and overall social norms. Should insurance fraud be ineffectively stopped, apart from impacting the friendly structure of the insurance system, its effect on the financial market should not be overlooked. Through case studies, this study investigated and inferred new modus operandi in insurance fraud. Currently, many countries have made related laws to oversee insurance fraud and insurance-related crime. However, Taiwan still uses the criminal code to penalize insurance fraud and insurance-related crimes without making specific legislation. This study also disclosed the difficulties that claim adjusters face when handling insurance claims and analyzed the determination criteria of claims adjusters. Currently, the grievance rate of claims is the main requirement relating to the new products submitted for approval by insurers. Therefore, apart from affecting the image and business promotion, the quality of claims will affect the operations, financial safety, and sustainable development of insurers. In view of the lack of effective risk control measures of insurers, this study recommended mechanisms for improving insurance fraud prevention to prevent evil people and gangs from fearlessly committing insurance fraud by exploiting the loopholes in provisions and the self-monitoring of insurers. Therefore, it is necessary to enhance the optimization and technology innovation of the system for the risk control of insurance fraud in order to capture opportunist fraud offenders and for the reference of insurers.
47
Lin, Tzu-Kuei, and 林子貴. "Research on Prevention of Auto Insurance Fraud." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/68180778244282444623.
Full textAbstract:
碩士崑山科技大學
企業管理研究所
104
The growing incidence of insurance fraud has become one of today's crime issues, which not only endanger the insurance market stability, but also affect the economic order of the country. How to make the prevention and control strategies effective has become the focus of the worldwide Insurance Supervisory. This study used case study, literature review, in-depth interview, and focus group interview from the industry, government, and academic experts, explored the following study topics: 1. Where profit was to be gained, no moral sense. 2. Insurance fraud crime had continuously regenerated, which would only have the transition of crime type or have the evolution of trick. Crime itself would not disappear. 3. Only the man who was close to the problem could solve it. 4. Stepping out with cautions, patience, and self-restraint to walk far. 5. Take precautions, get prepared before pouring rain. 6. Integrate every and each one in the industry by sharing information. And hence derived the following feasible tactical actions: 1. Set up the particular unit and assign the person in charge to deal with the relative issues. 2. Enhance internal education and on-job training to build up the curb of the prevention. 3. Firm internal audit and control to maintain the order. 4. Design the product with prudence and cautiousness and establish the database of fraud feature to systematically nose the trick out in the first place. 5. Integrate the notification mechanism and make well use of insurance fraud prevention platform. 6. Regularly share and exchange the information with other industry and expert to follow current trend. 7. Urge the government to pay much more attention to fraud crimes and to promote fraud prevention and control in people’s mind. 8. Prosecute fraud offenders with appropriate statute and clause to deter violators in futures. Hope this study will provide the insurance industry, following researcher, and authorities a well reference on prevention and control of insurance fraud.
48
Kuo, Tzu-Ping, and 郭姿萍. "A study on the Prevention of Insurance Fraud in Marine Insurance." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/10663448696547557711.
Full textAbstract:
碩士淡江大學
保險學系保險經營碩士班
95
“Insurance Fraud” has been an issue, since there exists the system of insurance. With the social events and relevant issues about insurance fraud keeping in aggravating recently. But the study about Insurance Fraud in Marine Insurance is too few. This paper collect those cases about Insurance Fraud in Marine Insurance. Therefore, this paper probed into “how to prevent Insurance Fraud in marine insurance from LAW and from RISK MANAGEMENT”. This paper would be analyzing the practical operation of an insurance company and trying to find out the feasibility of Insurance Fraud Prevention by using various kinds of risk management countermeasures. By which, this paper discovers the losses caused by insurance fraud could be prevented and/ or reduced. The followings are those risk management countermeasures studied and applied: A. The principle of “Risk Retention & Reduction” ; B. The principle of “Risk Avoidance or Hedging” ; C. The principle of “Risk Sharing & Diversification” ; D. The principle of “Risk Transference or Shift”.
49
Chen, XuanYu, and 陳炫宇. "A Study on Insurance Fraud Prevention Rules-Focus on Contigency Insurance." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/59615894221240808475.
Full textAbstract:
碩士國立中正大學
法律學研究所
101
There can not be avoided the discussion of insurance fraud since insurance system began. Rather, the formulation and revision of the insurance laws and regulations usually greatly associated with insurance fraud. In the case of rapid social change, whether Taiwan Insurance Law is sufficient to guard against insurance fraud occurs or not. That is what we want to discuss. There are various insurance fraud types in Taiwan insurance contract, and according the insurance contract process, we can divided into two stages: pre-contract stge and post-contract stge. At pre-contract stge, insured may fraudulent misrepresent, and pass through incontest period which Insurance Law § 64(3) was regulated. Insured or beneficiary could get unjust benefit. At post-contract stge, the insured may take out several hospital medical insurances. This would increase the probability of insurance fraud occurrance. For another, when insurance accident occurred, the insured may falsely misrepresent about his loss. In this situation, Taiwan Insurance Law didn't stipulate the regulation about fraudulent claim. This showed that Taiwan Insurance Law couldn't response to social change, and there's necessary to re-examine it. Recently, the major countries started to revise its Insurance Code, and the revision was according to current social situation of its country. For example, United Kingdom enacted Consumer (Disclosure and Misrepresentation) Insurance Act at 2012, which was partially replaced Marine Insurance Act 1906.Before the act was enacted, Marine Insurance Act 1906 applicated to all type of insurance contract. And in 2006, German modified its Insurance Contract Law greatly. In 2008, Japan enacted the Insurance Code to replace the regulation in Commercial Code Insurance Chapter. This article will consult the latest legislation of U.K. and Japan, trying to introduce the the relevant legislative system to prevent the occurrence of insurance fraud.
50
Lin, Chi-Chen, and 林琦珍. "Fraud detection using fraud triangle risk factors with data mining techniques." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/26938268609195324254.
Full textAbstract:
博士國立中正大學
會計與資訊科技研究所
99
The object of this study is to examine all aspects of fraud triangle and try to use available and public information to proxy variables measuring pressure/incentive, opportunity, and attitude/ rationalization, based on prior study and Statement on Auditing Standards. After identifying fraud indicators, I use Lawshe’s approach eliminates a total of 21 factors whose CVR (content validity ratio) values do not meet the criteria. As a Lawshe’s approach, the remaining 32 factors are considered by experts to be the measurements suitable for the assessment of fraud detection. In order to determine the relative weightings of the individual items, I design a hierarchical structure of questions for the AHP (analytic hierarchy process) questionnaires based on the above derived measurement dimensions and items. The result of AHP can find the three dimension of Fraud Triangle are difference weight for detecting fraud. The most important dimension experts consider is Pressure/Incentive, next dimension is Opportunity, and the lowest dimension is Attitude/rationalization. From the overall point, the top five important categories are “Poor performance”, “The need for external financing”, “Financial distress”, “Insufficient board oversight”, “Competition or market saturation”. According to the Lawshe’s approach, this study uses the key factors to development a fraud prediction model. Comparison with performance of different prediction models, ANNs (artificial neural network approach) is classified correctly greater than CART (classification and regression trees), and CART is classified correctly greater than logistic in both training and testing samples. In addition to, ANNs again has an inexpensive cost in overall of misclassification compared with CART, and CART has an inexpensive cost in overall of misclassification compared with logistic. Overview of comparison result of AHP, logistic, CART, and ANNs, the decision of experts are most consistent with CART prediction model. The gap with prediction model and experts judgment, one significant factor is “Historical restate frequency” of three prediction model unmatched with AHP. This study has practical implications for accounting practitioners, internal auditors, and fraud examiners. It provides prescriptive information on what fraud detection and prevention methods work best.