To see the other types of publications on this topic, follow the link: Credit card fraud.
Dissertations / Theses on the topic 'Credit card fraud'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 45 dissertations / theses for your research on the topic 'Credit card 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
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
2
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.
3
deMatos, Richard Bernard. "Floor limits and credit card fraud in the South African credit card industry." Thesis, University of South Africa, 2007. http://hdl.handle.net/10500/48.
Full textAbstract:
Credit card fraud losses within the South African credit card market in 2006 exceeded
R257M. A portion of these losses (R179M) are within the borders of South Africa and its
common monetary area partners. This represents a startling 70% of credit card fraud on
magnetic stripe cards used within the borders of South Africa.
The South African credit card industry adopts floor limits at certain merchants and
merchant categories. South Africa is one of a few countries in the world that still adopt
floor limits on credit cards within its payment card industry. Credit card transactions on
magnetic-stripe cards conducted below the merchant’s designated floor limit do not go to
the issuing bank for authorization. The first time the issuing bank acknowledges these
transactions is when they are settled on average two days later. The rationale for not
adopting zero floor limits within the South African credit card market is the supposed
inability of the existing telecommunications infrastructure to handle the volume and
frequency of data submitted by merchants for authorization. The impact of reduced fraud
and bad debt losses through adopting a zero floor limit in relation to merchant
operational costs is the basis of the research. The research also aims to examine the
Proposition that the existing telecommunications infrastructure is unable to support a
zero floor limit proposal.
4
Char, Shik-ngor Stephen. "Counterfeit credit card fraud : the process of professionalization and organisation /." [Hong Kong] : University of Hong Kong, 1994. http://sunzi.lib.hku.hk/hkuto/record.jsp?B13781248.
Full text
5
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
6
Dahabiyeh, Laila Ali. "IS security networks in credit card fraud prevention." Thesis, University of Warwick, 2017. http://wrap.warwick.ac.uk/88609/.
Full textAbstract:
In our increasingly connected world, maintaining the security of information systems is challenging. Today’s interconnected business environment calls for a change in how IS security is achieved to include thinking about the entire networks of relationships involved in preventing threats rather than just focusing on individual organizational security processes. Despite acknowledging the role of distributed and heterogeneous actors in achieving a secure environment, there is a lack of knowledge of how these actors actually prevent security threats. Moreover, the heterogeneity of actors involved gives rise to the issue of incentives needed to align their interests to ensure successful collective security efforts. This PhD thesis addresses these issues by zooming in on security networks, defined as collective efforts pursued by distributed actors to develop and adopt prevention measures to achieve security, to explain how these networks prevent security threats and identify the incentive mechanisms for converging the network’s heterogeneous actors. I challenge equilibrium and linearity assumptions identified in the current literature and argue for the need to adopt different theoretical and methodological approaches to uncover the dynamics in these networks. Through a historical case study of credit card fraud and how its prevention measures evolved over the last 55 years, I develop a process model of prevention encounters in security networks. The model depicts the dynamic and interactive nature of the prevention process and shows how the three proposed prevention mechanisms, namely, proposing solutions, resolving dissonance, and paving the way, interact to achieve prevention. The thesis further proposes three new forms of incentive mechanisms (transformative, preparatory, and captive) that are crucial for the survival of collective security efforts and show how they interact with the three prevention mechanisms. By this, this research complements the current security networks literature by offering a process model that explains how security networks achieve prevention. In addition, the interplay between the three incentive mechanisms reveals that incentives are not only ready-made structures or one-time event as depicted in the current literature but that they should also be seen as a socially dynamic process.
7
Char, Shik-ngor Stephen, and 查錫我. "Counterfeit credit card fraud: the process ofprofessionalization and organisation." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1994. http://hub.hku.hk/bib/B31977583.
Full text
8
Frank, Mari J. "Identity theft prevention and survival /." [Laguna Niguel, Calif.] : M.J. Frank and Associates, 1999. http://www.identitytheft.org.
Full textAbstract:
ID-theft survival kit -- Book From victim to victor -- ID theft FAQ -- Audiocassettes -- Identity theft resources -- Testimonials -- ID theft action letters -- About the author -- Media appearances -- Identity theft laws -- Theft Deterrence Act.Title from opening screen, December 28, 1999.
9
Lucas, Yvan. "Credit card fraud detection using machine learning with integration of contextual knowledge." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI110.
Full textAbstract:
La détection de fraude par carte de crédit présente plusieurs caractéristiques qui en font une tâche difficile. Tout d'abord, les attributs décrivant une transaction ignorent les informations séquentielles. Deuxièmement, les comportements d'achat et les stratégies de fraude peuvent changer au fil du temps, rendant progressivement une fonction de décision apprise par un classifieur non pertinente. Nous avons effectué une analyse exploratoire afin de quantifier le dataset shift jour par jour et avons identifé des périodes calendaires qui ont des propriétés différentes au sein du jeu de données. La stratégie principale pour intégrer des informations séquentielles consiste à créer un ensemble d'attributs qui sont des statistiques descriptives obtenues en agrégeant les séquences de transactions des titulaires de carte. Nous avons utilisé cette méthode comme méthode de référence pour la détection des fraudes à la carte de crédit. Nous avons proposé une stratégie pour la création d'attributs basés sur des modèles de Markov cachés (HMM) caractérisant la transaction par différents points de vue afin d'intégrer un large spectre d'informations séquentielles au sein des transactions. En fait, nous modélisons les comportements authentiques et frauduleux des commerçants et des détenteurs de cartes selon deux caractéristiques univariées: la date et le montant des transactions. Notre approche à perspectives multiples basée sur des HMM permet un prétraitement automatisé des données pour modéliser les corrélations temporelles. Des expériences menées sur un vaste ensemble de données de transactions de cartes de crédit issu du monde réel (46 millions de transactions effectuées par des porteurs de carte belges entre mars et mai 2015) ont montré que la stratégie proposée pour le prétraitement des données basé sur les HMM permet de détecter davantage de transactions frauduleuses quand elle est combinée à la stratégie de prétraitement des données par aggrégationsThe detection of credit card fraud has several features that make it a difficult task. First, attributes describing a transaction ignore sequential information. Secondly, purchasing behavior and fraud strategies can change over time, gradually making a decision function learned by an irrelevant classifier. We performed an exploratory analysis to quantify the day-by-day shift dataset and identified calendar periods that have different properties within the dataset. The main strategy for integrating sequential information is to create a set of attributes that are descriptive statistics obtained by aggregating cardholder transaction sequences. We used this method as a reference method for detecting credit card fraud. We have proposed a strategy for creating attributes based on Hidden Markov Models (HMMs) characterizing the transaction from different viewpoints in order to integrate a broad spectrum of sequential information within transactions. In fact, we model the authentic and fraudulent behaviors of merchants and cardholders according to two univariate characteristics: the date and the amount of transactions. Our multi-perspective approach based on HMM allows automated preprocessing of data to model temporal correlations. Experiments conducted on a large set of data from real-world credit card transactions (46 million transactions carried out by Belgian cardholders between March and May 2015) have shown that the proposed strategy for pre-processing data based on HMMs can detect more fraudulent transactions when combined with the Aggregate Data Pre-Processing strategy
10
Ehramikar, Soheila. "The enhancement of credit card fraud detection systems using machine learning methodology." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0023/MQ50338.pdf.
Full text
11
Jurgovsky, Johannes [Verfasser], Michael [Akademischer Betreuer] Granitzer, Sylvie [Akademischer Betreuer] Calabretto, and Pierre-Edouard [Akademischer Betreuer] Portier. "Context-Aware Credit Card Fraud Detection / Johannes Jurgovsky ; Michael Granitzer, Sylvie Calabretto, Pierre-Edouard Portier." Passau : Universität Passau, 2019. http://d-nb.info/1202145396/34.
Full text
12
Darling, Robert J. "Marine Corps unit-level internal management controls for the government-wide commercial purchase card /." Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2003. http://library.nps.navy.mil/uhtbin/hyperion-image/03Dec%5FDarling%5FMBA.pdf.
Full text
13
Lucas, Yvan [Verfasser], and Michael [Akademischer Betreuer] Granitzer. "Credit card fraud detection using machine learning with integration of contextual knowledge / Yvan Lucas ; Betreuer: Michael Granitzer." Passau : Universität Passau, 2020. http://d-nb.info/1213520304/34.
Full text
14
Downing, Christopher O'Brien Jr. "Intervening to Increase the ID-Checking Behavior of Cashiers: Cashier-Focused vs. Customer-Focused Approaches." Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/52937.
Full textAbstract:
The present four field studies explored the effectiveness of multiple prevention techniques designed to increase the frequency of cashiers' identification (ID)-checking behaviors from a customer-focused and cashier-focused approach. Studies 1 and 2 examined customer-focused approaches, whereas Study 3 examined a cashier-focused approach. Study 4 examined a combination of the cashier-focused and customer-focused approaches.
From a customer approach, Study 1 investigated the use of four prompts (a no-prompt control, an antecedent only, an antecedent with a positive consequence, and an antecedent with a negative consequence) at encouraging cashiers to ask customers for their ID during a credit purchase. Research assistants (RAs) visited various stores and made credit purchases, while displaying one of the four prompts covering their card's signature line to the cashier during check-out. The results showed RAs were checked for ID the most when using the prompts containing the antecedent and consequence, which was checked for ID significantly more than the no-prompt control.
Study 2 (also a customer approach) attempted to replicate Study 1 in a non-college community. Using a similar methodology as Study 1, the results showed RAs were checked for ID the most when using the prompt with the antecedent and positive consequence, which was checked for ID significantly more than the no-prompt control.
From a cashier approach, Study 3 investigated the use of a goal-setting and prompt intervention led by the restaurant manager to increase the frequency of cashiers' ID-checking behavior. Using an A-B-A (Baseline-Intervention-Withdrawal) reversal design at one of two restaurants, the results showed the intervention restaurant's percentage of ID-checked purchases increased from Baseline to the Intervention phase. But, it decreased slightly during the Withdrawal phase, showing functional control but also some maintenance over the target behavior. The percentage of ID-checked purchases at the control restaurant was almost nonexistent throughout the study.
Study 4 investigated the impact of using two intervention approaches (i.e., the customer and cashier approach) as opposed to one (i.e., the customer approach) to increase the frequency of cashiers' ID-checking behavior. While the A-B-A phases were occurring in the restaurants used in Study 3, RAs entered the restaurants and displayed an antecedent and positive consequence prompt to the cashiers during a credit purchase. The results of Study 4 partially supported the hypothesis. The cashiers in the intervention restaurant significantly checked more RAs for ID when two intervention approaches were combined than when only one intervention approach was used during Baseline, but not during the Withdrawal phase.Ph. D.
15
Downing, Christopher O'Brien Jr. "Developing a Practical Intervention to Prevent Identity Theft: A Behavioral-Science Field Study." Thesis, Virginia Tech, 2010. http://hdl.handle.net/10919/41968.
Full textAbstract:
Cashiers' identification-checking behaviors were observed at two grocery stores with the aim to actively involve cashiers in decreasing credit-card fraud. After baseline observations, cashiers at one store received a participative goal-setting and feedback intervention, whereby they collaboratively set a store goal for checking customers' identification. Over 23 days, the cashiers received one-to-one verbal feedback on their store's identification-checking percentages. The percentage of identification-checked purchases at the intervention store increased from 0.2 percent at Baseline to 9.7 percent during the Intervention. Then, it declined to 2.3 percent during Withdrawal, showing functional control of the intervention over the cashiers' target behavior. The cashiers at the other store served as the control group, and their percentage of identification-checked purchases were 0.3 percent, 0.4 percent, and 0.7 percent respectively during each of the A-B-A phases at the intervention store. It was also found the intervention affected male cashiers more than female cashiers. The present study also assessed the social validity of the current intervention by surveying both customers and cashiers from the intervention store. The results showed that customers do not mind getting their ID checked, while cashiers consider it important to check a customer for identification during a credit purchase.Master of Science
16
Sun, Yan. "An investigation into financial fraud in online banking and card payment systems in the UK and China." Thesis, Loughborough University, 2011. https://dspace.lboro.ac.uk/2134/8290.
Full textAbstract:
This doctoral thesis represents an investigation into financial fraud in online banking and card payment systems in the UK and China, involving network security, online financial transactions, internet fraud, card payment systems and individuals' perception of and behaviours towards electronic environments. In contrast to previous studies, the research questions were tackled by survey questionnaires both in the UK and China, with a particular interest in fraud and attempted fraud. The main findings from the UK respondents were that those with higher IT skill and younger respondents are more likely to be defrauded on the internet. Certain types of online activities are associated with higher risks of fraud, these being internet banking; online shopping and media downloading. Furthermore, four predictors (internet banking, online education services, downloading media and length of debit card usage) provided significant effects in the logistic regression model to explain fraud occurrence in the UK. Based on the data collected in China, younger respondents were more likely to have higher general IT skill and higher educational qualifications. However, online shopping was the only online activity which was significantly correlated to fraud occurrence. Finally, two predictors (frequency of usage of online shopping and number of debit cards) were selected in the logistic regression model to explain fraud occurrence in China.
17
Wilson, Belinda R. "The Forgotten Signature: An Observational Study on Policy of Securing Identity in Prevention of Identity Theft and Credit/Debit Card Fraud at Retail Store POS Terminals." Digital Commons @ East Tennessee State University, 2016. https://dc.etsu.edu/etd/3074.
Full textAbstract:
Identity theft and credit and bank card fraud is increasing in America and worldwide. Given the current statistics of its prevalence and practices around the world, many in government are starting to take critical notice due to its impact on a nation’s economy. Limited amounts of research have been conducted regarding the practices of applying the Routine Activities Theory (Cohen & Felson, 1979) to better equip store managers in understanding the critical need for capable and effective point of sale guardianship for in-store prevention of credit or bank card fraud due to identity theft. This research has used qualitative observational studies to investigate the presence of or lack of capable guardianship at point of sales transactions in large department stores where a majority of in-store credit and bank card fraud loss occurs. Findings conclude an overwhelming lack of capable guardianship at retail store POS terminals.
18
Ludvigsen, Jesper. "Handling Imbalanced Data Classification With Variational Autoencoding And Random Under-Sampling Boosting." Thesis, Uppsala universitet, Statistiska institutionen, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-412838.
Full textAbstract:
In this thesis, a comparison of three different pre-processing methods for imbalanced classification data, is conducted. Variational Autoencoder, Random Under-Sampling Boosting and a hybrid approach of the two, are applied to three imbalanced classification data sets with different class imbalances. A logistic regression (LR) model is fitted to each pre-processed data set and based on its classification performance, the pre-processing methods are evaluated. All three methods shows indications of different advantages when handling class imbalances. For each pre-processed data, the LR-model has is better at correctly classifying minority class observations, compared to a LR-model fitted to the original class imbalanced data sets. Evaluating the overall classification performance, both VAE and RUSBoost shows improving classification results while the hybrid method performs worse for the moderate class imbalanced data and best for the highly imbalanced data.
19
Santiago, Gabriel Preti. "Um processo para modelagem e aplicação de técnicas computacionais para detecção de fraudes em transações eletrônicas." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/45/45134/tde-23052014-144032/.
Full textAbstract:
Nos últimos anos, tem-se observado um aumento significativo no volume de transações financeiras realizadas pela Internet. Esse crescimento no volume financeiro, associado à fragilidade inerente à ausência de verificações básicas, possíveis somente em transações do mundo físico, tem atraído a atenção de pessoas com o objetivo de obter vantagens financeiras de forma ilícita. Devido aos prejuízos causados pelas fraudes, surgiram empresas de pagamento online com o objetivo de tornar as transações de compra e venda na Internet mais seguras. Essas empresas atuam como um intermediário das transações e assumem os riscos associados, mostrando-se ser esse um negócio de alto risco. Dado o alto volume de transações com as quais essas empresas precisam lidar, torna-se clara a necessidade de métodos computacionais para detecção de transações fraudulentas, visto que a utilização estrita de verificações manuais é inviável para lidar com tal volume de transações. Essa tarefa de análise e identificação de transações fraudulentas pode ser vista como um problema computacional de classificação, sendo então aplicáveis técnicas de classificação, aprendizado computacional e mineração de dados. Porém, dada a complexidade do problema, a aplicação de técnicas computacionais só é possível após um profundo entendimento do problema e a definição de uma modelagem eficiente associada a um processo consistente e abrangente, capaz de lidar com todas as etapas necessárias para a análise eficiente de uma transação. Face a isso, o presente trabalho propõe uma abordagem abrangente para tratar o problema da fraude nesse novo mercado de intermediação de pagamentos online utilizando como base um processo já muito bem estabelecido na indústria. Abordaremos mais especificamente uma das fases desse processo, que se refere justamente a utilização de ferramentas computacionais para a detecção das fraudes, e apresentaremos um sub-processo que envolve a utilização de várias ferramentas para o tratamento do ponto de vista computacional do problema de detecção de fraudes. Para a validação dos resultados da proposta, utilizaremos uma enorme quantidade de dados reais disponibilizados por uma grande empresa do setor de intermediação de pagamentos online que colaborou com nossa pesquisa.In recent years, there has been a significant increase in the volume of electronic transactions in the Web. This growth in trading volume, associated with the risks caused by the absence of basic checks, possible only in transactions of the physical world, has attracted the attention of people with the intention of taking advantage to obtain illicit financial benefits. Due to the injuries caused by fraud, online payment service companies emerged, with the goal of making Web transactions safer. These companies act as an intermediary between buyers and sellers, assuming all the risks, and so it is clear that it is a high-risk business. Given the high volume of transactions with which these companies must deal, it is clear the need for computational methods for detecting fraudulent transactions, as the strict use of manual checks is infeasible to handle such a volume. The task of analysis and identification of fraudulent transactions can be seen as a classification problem, and so classification, data mining and machine learning techniques can be applied to it. However, given the complexity of the problem, the application of computational techniques is only possible after a thorough understanding of the problem and the definition of an efficient model, associated with a consistent and comprehensive process which would be able to handle all the steps needed to analyze a transaction in an efficient way. Given this scenario, this work proposes a comprehensive approach to address the problem of fraud in this new business of online payment intermediation, using as basis a process already established in the industry. We will discuss more specifically one of the phases of this process, which refers to the use of computational tools to detect frauds, and we will present a sub-process using several tools to deal with the problem from a computational point of view. To validate our results, we will use a huge amount of real data provided by an important company of the online payment industry, which cooperated with our research.
20
Beraldi, Fidel. "Atualização dinâmica de modelo de regressão logística binária para detecção de fraudes em transações eletrônicas com cartão de crédito." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/45/45134/tde-05022015-232801/.
Full textAbstract:
Com o avanço tecnológico e econômico, que facilitaram o processo de comunicação e aumento do poder de compra, transações com cartão de crédito tornaram-se o principal meio de pagamento no varejo nacional e internacional (Bolton e Hand , 2002). Neste aspecto, o aumento do número de transações com cartão de crédito é crucial para a geração de mais oportunidades para fraudadores produzirem novas formas de fraudes, o que resulta em grandes perdas para o sistema financeiro (Chan et al. , 1999). Os índices de fraudes têm mostrado que transações no comércio eletrônico (e-commerce) são mais arriscadas do que transações presencias em terminais, pois aquelas não fazem uso de processos seguros e eficientes de autenticação do portador do cartão, como utilização de senha eletrônica. Como os fraudadores se adaptam rapidamente às medidas de prevenção, os modelos estatísticos para detecção de fraudes precisam ser adaptáveis e flexíveis para evoluir ao longo do tempo de maneira dinâmica. Raftery et al. (2010) desenvolveram um método chamado Dynamic Model Averaging (DMA), ou Ponderação Dinâmica de Modelos, que implementa um processo de atualização contínuo ao longo do tempo. Nesta dissertação, desenvolvemos modelos DMA no espaço de transações eletrônicas oriundas do comércio eletrônico que incorporem as tendências e características de fraudes em cada período de análise. Também desenvolvemos modelos de regressão logística clássica com o objetivo de comparar as performances no processo de detecção de fraude. Os dados utilizados para tal são provenientes de uma empresa de meios de pagamentos eletrônico. O experimento desenvolvido mostra que os modelos DMA apresentaram resultados melhores que os modelos de regressão logística clássica quando analisamos a medida F e a área sob a curva ROC (AUC). A medida F para o modelo DMA ficou em 58% ao passo que o modelo de regressão logística clássica ficou em 29%. Já para a AUC, o modelo DMA alcançou 93% e o modelo de regressão logística clássica 84%. Considerando os resultados encontrados para os modelos DMA, podemos concluir que sua característica de atualização ao longo do tempo se mostra um grande diferencial em dados como os de fraude, que sofrem mudanças de comportamento a todo momento. Deste modo, sua aplicação se mostra adequada no processo de detecção de transações fraudulentas no ambiente de comércio eletrônico.Regarding technological and economic development, which made communication process easier and increased purchasing power, credit card transactions have become the primary payment method in national and international retailers (Bolton e Hand , 2002). In this scenario, as the number of transactions by credit card grows, more opportunities are created for fraudsters to produce new ways of fraud, resulting in large losses for the financial system (Chan et al. , 1999). Fraud indexes have shown which e-commerce transactions are riskier than card present transactions, since those do not use secure and efficient processes to authenticate the cardholder, such as using personal identification number (PIN). Due to fraudsters adapt quickly to fraud prevention measures, statistical models for fraud detection need to be adaptable and flexible to change over time in a dynamic way. Raftery et al. (2010) developed a method called Dynamic Model Averaging (DMA), which implements a process of continuous updating over time. In this thesis, we develop DMA models within electronic transactions coming from ecommerce environment, which incorporate the trends and characteristics of fraud in each period of analysis. We have also developed classic logistic regression models in order to compare their performances in the fraud detection processes. The database used for the experiment was provided by a electronic payment service company. The experiment shows that DMA models present better results than classic logistic regression models in respect to the analysis of the area under the ROC curve (AUC) and F measure. The F measure for the DMA was 58% while the classic logistic regression model was 29%. For the AUC, the DMA model reached 93% and the classical model reached 84%. Considering the results for DMA models, we can conclude that its update over time characteristic makes a large difference when it comes to the analysis of fraud data, which undergo behavioral changes continuously. Thus, its application has proved to be appropriate for the detection process of fraudulent transactions in the e-commerce environment.
21
Ghemmogne, Fossi Leopold. "Gestion des règles basée sur l'indice de puissance pour la détection de fraude : Approches supervisées et semi-supervisées." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI079.
Full textAbstract:
Cette thèse traite de la détection de fraude par carte de crédit. Selon la Banque Centrale Européenne, la valeur des fraudes utilisant des cartes en 2016 s'élevait à 1,8 milliard d'euros. Le défis pour les institutions est de réduire ces fraudes. En règle générale, les systèmes de détection de la fraude sont consistués d'un système automatique construit à base de règles "si-alors" qui contrôlent toutes les transactions en entrée et déclenchent une alerte si la transaction est considérée suspecte. Un groupe expert vérifie l'alerte et décide si cette dernière est vrai ou pas. Les critères utilisés dans la sélection des règles maintenues opérationnelles sont principalement basés sur la performance individuelle des règles. Cette approche ignore en effet la non-additivité des règles. Nous proposons une nouvelle approche utilisant des indices de puissance. Cette approche attribue aux règles un score normalisé qui quantifie l'influence de la règle sur les performances globales du groupe de règles. Les indice utilisés sont le "Shapley Value" et le "Banzhaf Value". Leurs applications sont: 1) Aide à la décision de conserver ou supprimer une règle; 2) Sélection du nombre k de règles les mieux classées, afin de travailler avec un ensemble plus compact. En utilisant des données réelles de fraude par carte de crédit, nous montrons que: 1) Cette approche permet de mieux évaluer les performances du groupe plutot que de les évaluer isolément. 2) La performance de l'ensemble des règles peut être atteinte en conservant le dixième des règles. Nous observons que cette application peut être comsidérée comme une tâche de sélection de caractéristiques:ainsi nous montrons que notre approche est comparable aux algorithmes courants de sélection des caractéristiques. Il présente un avantage dans la gestion des règles, car attribue un score normalisé à chaque règle. Ce qui n'est pas le cas pour la plupart des algorithmes, qui se concentrent uniquement sur une solution d'ensemble. Nous proposons une nouvelle version du Banzhaf Value, à savoir le k-Banzhaf; qui surclasse la précedente en terme de temps de calcul et possède des performances comparables. Enfin, nous mettons en œuvre un processus d’auto-apprentissage afin de renforcer l’apprentissage dans un algorithme. Nous comparons ces derniers avec nos trois indices de puissance pour effectuer une classification sur les données de fraude par carte de crédit. En conclusion, nous observons que la sélection de caractéristiques basée sur les indices de puissance a des résultats comparables avec les autres algorithmes dans le processus d'auto-apprentissageThis thesis deals with the detection of credit card fraud. According to the European Central Bank, the value of frauds using cards in 2016 amounted to 1.8 billion euros. The challenge for institutions is to reduce these frauds. In general, fraud detection systems consist of an automatic system built with "if-then" rules that control all incoming transactions and trigger an alert if the transaction is considered suspicious. An expert group checks the alert and decides whether it is true or not. The criteria used in the selection of the rules that are kept operational are mainly based on the individual performance of the rules. This approach ignores the non-additivity of the rules. We propose a new approach using power indices. This approach assigns to the rules a normalized score that quantifies the influence of the rule on the overall performance of the group. The indexes we use are the Shapley Value and Banzhaf Value. Their applications are 1) Decision support to keep or delete a rule; 2) Selection of the number k of best-ranked rules, in order to work with a more compact set. Using real credit card fraud data, we show that: 1) This approach performs better than the one that evaluates the rules in isolation. 2) The performance of the set of rules can be achieved by keeping one-tenth of the rules. We observe that this application can be considered as a task of selection of characteristics: We show that our approach is comparable to the current algorithms of the selection of characteristics. It has an advantage in rule management because it assigns a standard score to each rule. This is not the case for most algorithms, which focus only on an overall solution. We propose a new version of Banzhaf Value, namely k-Banzhaf; which outperforms the previous in terms of computing time and has comparable performance. Finally, we implement a self-learning process to reinforce the learning in an automatic learning algorithm. We compare these with our power indices to rank credit card fraud data. In conclusion, we observe that the selection of characteristics based on the power indices has comparable results with the other algorithms in the self-learning process
22
Ramos, Jhonata Emerick. "Redes bayesianas aplicadas à modelagem de fraudes em cartão de crédito." reponame:Repositório Institucional do FGV, 2015. http://hdl.handle.net/10438/14062.
Full textAbstract:
Submitted by Jhonata Ramos (jhonata.emerick@gmail.com) on 2015-09-18T16:47:09Z
No. of bitstreams: 1
dissertacao_final.pdf: 820128 bytes, checksum: b7fc5ca71a3debaf99da902b518ff748 (MD5)Approved for entry into archive by Renata de Souza Nascimento (renata.souza@fgv.br) on 2015-09-18T17:17:43Z (GMT) No. of bitstreams: 1 dissertacao_final.pdf: 820128 bytes, checksum: b7fc5ca71a3debaf99da902b518ff748 (MD5)
Made available in DSpace on 2015-09-18T21:34:00Z (GMT). No. of bitstreams: 1 dissertacao_final.pdf: 820128 bytes, checksum: b7fc5ca71a3debaf99da902b518ff748 (MD5) Previous issue date: 2015-08-21
For fraud detection models are used to identify whether a transaction is legitimate or fraudulent based on registration and transactional information. The proposal on technical study presented in this thesis consists in the Bayesian Networks (BN); their results were compared to logistic regression technique (RL), widely used by the market. Bayesian classifiers were evaluated, with the Naive Bayes structure. The structures of Bayesian networks were obtained from actual data, provided by a financial institution. The database was divided into samples development and validation by cross validation ten partitions. Naive Bayes classifiers were chosen due to the simplicity and efficiency. The model performance was evaluated taking into account the confusion matrix and the area under the ROC curve. The analyzes of performance models revealed slightly higher than the logistic regression compared to bayesian classifiers. Logistic regression was chosen as the most appropriate model for performed better in predicting fraudulent operations, compared to the confusion matrix. Based on area under the ROC curve, logistic regression demonstrated greater ability to discriminate the operations being classified correctly, those that are not.
Modelos para detecção de fraude são utilizados para identificar se uma transação é legítima ou fraudulenta com base em informações cadastrais e transacionais. A técnica proposta no estudo apresentado, nesta dissertação, consiste na de Redes Bayesianas (RB); seus resultados foram comparados à técnica de Regressão Logística (RL), amplamente utilizada pelo mercado. As Redes Bayesianas avaliadas foram os classificadores bayesianos, com a estrutura Naive Bayes. As estruturas das redes bayesianas foram obtidas a partir de dados reais, fornecidos por uma instituição financeira. A base de dados foi separada em amostras de desenvolvimento e validação por cross validation com dez partições. Naive Bayes foram os classificadores escolhidos devido à simplicidade e a sua eficiência. O desempenho do modelo foi avaliado levando-se em conta a matriz de confusão e a área abaixo da curva ROC. As análises dos modelos revelaram desempenho, levemente, superior da regressão logística quando comparado aos classificadores bayesianos. A regressão logística foi escolhida como modelo mais adequado por ter apresentado melhor desempenho na previsão das operações fraudulentas, em relação à matriz de confusão. Baseada na área abaixo da curva ROC, a regressão logística demonstrou maior habilidade em discriminar as operações que estão sendo classificadas corretamente, daquelas que não estão.
23
CHEN, PEI-YU, and 陳佩妤. "Predicting Credit Card Fraud by Deep Learning." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/x77ee4.
Full textAbstract:
碩士世新大學
資訊管理學研究所(含碩專班)
106
With the popularity of online shopping, cases of transaction fraud are also increasing. According to statistics, the amount of losses from credit card fraud is nearly 2 billion annually in Taiwan. In order to prevent fraud events, many studies have used machine learning methods to detect credit card fraud in recent years. One of the challenges of these methods is that the credit card transaction data is highly imbalanced, fraudulent transactions are largely outnumbered by genuine ones. A common strategy for dealing with the problem is to under-sample the legit transaction class in the training set. In addition, machine learning algorithms need to perform data pre-processing first, and select features that are beneficial to the training process. However, due to confidentiality issues, a publicly available credit card data set is usually encrypted or transformed which make it difficult to select proper attributes to train the classifier algorithms. However, there is no need to select features while establishing a deep learning model. The deep learning approach has advantages for processing confidential data such as credit card transactions. In this study, the credit card transaction data obtained was first under-sampled and the ratio of fraud transactions to legit ones was adjusted to 50%, 15%, 10%, 5%, and 1% for comparison. Since the attribute names in the data set have been transformed except for transaction time and transaction amount. Therefore, we randomly selected the attributes to investigate the performance of Logistic Regression, Random Forest, and Support Vector Machine. In addition, we used Keras to build a deep learning model which includes an input layer and three hidden layers, and conducted 200 times of training. Five metrics were used to report the performance of fraud detection classifiers including Accuracy, Precision, Recall, F1-Score, and Matthews correlation coefficient. The experimental results show that the deep learning method, in most circumstance, is outperform the machine learning methods.
24
Wang, Chao-Wei, and 汪昭緯. "Apply Clustering to detect Credit Card fraud transaction." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/04403719218805902367.
Full text
25
Lai-Chen, Chen, and 陳來成. "Credit Card Fraud Detection Using Data Mining Approaches." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/51921731728470410399.
Full textAbstract:
碩士元智大學
資訊管理學系
90
Credit card transactions and electronic commerce continue to grow in great number. The higher rate of fraudulent account numbers also growing fast in credit card industries that subsequent losses by banks. Improved fraud detection thus has become essential to maintain the viability of commercial banks and the countries payment system. The prevention of credit card fraud is an application for prediction techniques. This paper shows how data mining techniques and artificial intelligence algorithms can be successfully to obtain a high fraud detection rate. We also describe an AI-based approach that construct and compare predict models separately by case-based reasoning, decision tree and neural network methods for detecting fraud pattern. To ensure proper model construction that concept had to be developed and tested on real credit card data of local bank. The prediction of user behavior and operation transaction can be integrated and implemented on the fraud detection models.
26
Tseng, Yueh Chin, and 曾月金. "A Study on Credit Card Fraud Detection Model." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/62427476051743309532.
Full textAbstract:
碩士銘傳大學
資訊管理學系碩士在職專班
91
As issuing banks progressively strive for promoting the utilization rate of credit cards to expedite their markets, frauds with credit cards are also continually growing. The amount of issued cards has been beyond 60 millions and the amount of used cards beyond 34 millions in Taiwan in one year by 2003. It is possible that one person can own more than one card. When the market speed up, the fraud of cards are simultaneously rising. It is believed that the banks have encountered a huge money loss beyond 30 billions in this year. The cardholders also worry about the risk of card frauds. In this thesis, we are concerning about the feasibility of adopting data mining techniques to develop an effective fraud detection system for credit cards. Due to the constraint caused by the privacy and safety problem of real transaction data, in this study a simulation program is coded to generate artifact transactions for simulation testing. We propose an integrated approach for dealing with the fraud detection problem. A clustering method is first applied to build a classification model for potential fraud transactions. Those transactions fall into this fraud group will be claimed to be in the warning list for further validation. On the other hand, those transactions falls outside of the fraud group are sent to the second classification module that might be built through the decision tree model or neural networks. Through a set of simulation experiments, it is shown that this integrated fraud detection approach is possible to reduce the detection errors. It was worth to study further transaction fraud detection of module.
27
CHEN, YA-SIN, and 陳雅馨. "Credit Card Fraud Detection using Hidden Markov Model." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/u4em2k.
Full textAbstract:
碩士東海大學
統計學系
107
Credit card payment has strongly growing due to easy access to internet and innovations in e-commerce technology. The number of transactions has increased dramatically not only on regular credit card consumption but also on fraud events. Identifying fraudulent transactions and establishing an efficient fraud detection system (FDS) have become major issues in the financial industry as costs of credit card can bring substantial losses for financial industry. By regarding the true-fraud transactions as hidden states, this thesis applies a hidden Markov model (HMM) to analyze the sequence of operation in credit card transaction processing and shows how it can be used for detecting fraud. An HMM is a doubly stochastic process with an underlying Markov process that is not directly observable but can be inferred by analyzing another set of stochastic process which produces the sequence of observations. In practice, testing FDS is difficult as banks usually do not agree to share their data with researchers as well as no benchmark data set are available. To evaluate the efficiency of the HMM-based FDS, we consider three criteria, namely, true positive rate, false positive rate and overall accuracy. Simulation results show that the proposed HMM-based FDS performs more efficiently in terms of true positive rate compared with false positive rate. Overall, the HMM-based FDS performs well in terms of overall accuracy.
28
GARG, ANUMEHA. "CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING TECHNIQUES." Thesis, 2022. http://dspace.dtu.ac.in:8080/jspui/handle/repository/19225.
Full textAbstract:
Over the previous few decades, the increasing credit card fraud cases has always been
a major source of concern. This situation is because of the widespread of new
technologies, particularly the growing popularity of online banking transactions.
However, to recognize scam tendencies it takes computational strength and
complexity in designing and creating the pattern matching rule basis. The major
purpose is to identify methods and strategies that have significant influence on fraud
detection, with a focus on existing research work. Support Vector Machines (SVMs),
naive Bayesian, Artificial Neural Networks (ANNs), Decision Tree, K-Nearest
Neighbor (k-NN) and Frequent Pattern Mining algorithms are all studied and
compared for detecting suspicious transactions.
Ensemble models like bagging and clustering have been utilized in conjunction with
an algorithmic technique. Boosting has been performed to a dataset of 284807
transactions that is significantly skewed. To name a few only 492 of the total
transactions have been flagged as suspicious. Models of prediction, such asthe logistic
as well as XGBoost when used with various resampling approaches have yielded. It
has been used to determine a transaction is genuine or fraudulent. The model's
performance is assessed using the following criteria: recall, precision, f1-score,
precision-recall (PR) curve, and receiver operating characteristics (ROC) curves.
29
Wang, Kuo-Ching, and 王國瑾. "Using Hilbert-Huang Transform For Credit Card Fraud Forecasting." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/20247408431612379212.
Full textAbstract:
碩士東吳大學
企業管理學系
99
Abstract Financial time series are inherently nonlinear and non-stationary, it is therefore difficult using statistical models to forecast. ANN (Artificial Neural Networks) does not require strict theoretical assumptions, so it has been applied in a wide range areas for time series forecasting. On ANN learning algorithms, the ELM (Extreme Learning Machine) overcomes the drawback of traditional Back-propagation. Inaddition,HHT (Hilbert-Huang Transform) can effectively analyze data on both nonlinear and non-stationary status. This study takes the credit card fraud amount as research subjects during the period of 2005 to 2010. We propose a hybrid forecasting model based on HHT and ELM. Firstly, by using HHT to decompose credit card fraud amount into several IMF(Intrinsic Mode Functions) and each IMF component is modeled by individual ELM respectively. The result shows that HHT can effectively improve ELM models prediction accuracy. Two models in combination would be more accurate than a single model. Keywords: Credit Card Fraud, Hilbert-Huang Transform, Extreme Learning Machine.
30
Liao, Yuan-hung, and 廖元宏. "Credit Card Fraud, Prevention and Counterfeit Immigration in Taiwan." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/41663817638744775398.
Full textAbstract:
碩士世新大學
法律學研究所(含碩專班)
93
The credit card is so popular currently around the world for it's ability to play an important role of convenient payment tool. With high development of technology and the coming of knowledge-economy, not only the credit card business has been diversified, but the fraud risk has increased continuously. Hence bank is facing the greatest challenge and focusing on how to manage and control the serious fraud risk, as well as to promote the service quality. In view of the increase in credit card issuing, utility ratio and also fraud cases, first of all, this research is going to analyze criminal types with respective characteristics, fraud skills and to discuss future development based on criminal psychology. As overseas fraud groups take chance to migrate credit card forgery skills into Taiwan and together to cooperate with local fraud groups, this has resulted in the increase of credit card fraud cases and damage of rights/interests to customers, and banks with bearing bad debt risk. Due to the fact that credit card crime has been internationalized and grouped, secondly, this research is also to point out current and future credit card problems and to work out the prevention and precaution. Finally, to gather people in public to look into seriously credit card crime and develop the strategy of precaution, and further to remove this negative image as " Taiwan is a Kingdom/Heaven of Fraud and Forgery" are main topics for the purpose of protecting the consumer market and promoting banking business and environment to be more competitive all over the word.
31
Yi-Chien, Feng, and 馮益堅. "Focusing on credit card fraud criminal to develop the strategy of banker’s fraud control." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/77993394747233987695.
Full textAbstract:
碩士輔仁大學
企業管理學系管理學碩士在職專班
100
This study focus on the fraud criminal model which related to Credit Card and expect to find the security risk & weak in card business management and find the way on banking sight to control it for reduce user or bank’s loss and prevent criminal event. This study using case study due to writer is working in a global bank security & investigation department and in charge of this department country part which will convenience to get some raw data for study, this include the credit card business procedure, working flow, audit & risk management, card fraud cases & its development. Studying step is collect credit card related fraud case & bank internal cards business regulation, procedure & process flow chart, than depend on those criminal model to analyst its related, try to fine the weak in bank and the strategy. The anti-criminal strategy which this study found should suit for all local banks due to all banks issuing the same several global credit cards and all process procedure is base on FSC regulation, and FSC will also audit all of bank to find the process weak and asking revise.
32
Pun, Joseph King-Fung. "Improving Credit Card Fraud Detection using a Meta-learning Strategy." Thesis, 2011. http://hdl.handle.net/1807/31396.
Full textAbstract:
One of the issues facing credit card fraud detection systems is that a significant percentage of transactions labeled as fraudulent are in fact legitimate. These “false alarms” delay the detection of fraudulent transactions. Analysis of 11 months of credit card transaction data from a major Canadian bank was conducted to determine savings improvements that can be achieved by identifying truly fraudulent transactions. A meta-classifier model was used in this research. This model consists of 3 base classifiers constructed using the k-nearest neighbour, decision tree, and naïve Bayesian algorithms. The naïve Bayesian algorithm was also used as the meta-level algorithm to combine the base classifier predictions to produce the final classifier. Results from this research show that when a meta-classifier was deployed in series with the Bank’s existing fraud detection algorithm a 24% to 34% performance improvement was achieved resulting in $1.8 to $2.6 million cost savings per year.
33
Shen, Lin-chih, and 林智盛. "A Study of Credit Card Fraud Behavior On the Internet." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/tam5ss.
Full textAbstract:
碩士世新大學
財務金融學研究所(含碩專班)
96
The era of e-commerce is coming. Shopping on internet, one kind of new consumer habit has gradually become as a part of people's lives. Local bank treat credit card promotion as a key business strategy due to credit card business surge. It's not only the marketing scale of EC in Taiwan expanding to 18.547 billion dollars , but also EC company numbers growing up to 16,982 by 2007. E-commerce mode and internet environment are developed well so that it contributes more internet shopping. Moreover, the fraud of credit card shopping on internet is continually revealed too. Shopping on internet is not a personally trade, it is difficult to prevent fraud behavior on internet by only auditing card number. EC companies are forced to bear the loss. It’s a hard task for EC companies to prevent from the fraud. If there is an alert system, the EC companies can decrease the loss. In this study, 11 variables are verified by Logistic analysis, the lowest of the summary of typeⅠand type Ⅱ error is the cut-point. The study finds the variables which will positive affect the credit card fraud behavior on the internet. EC companies can prevent the fraud by check the variables. Furthermore, it could be beneficial to decrease the loss of EC companies.
34
Luo-Shu-TIng and 羅書婷. "Application of Personlized Approaches to Detection of Credit Card Fraud." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/20253784120594360626.
Full textAbstract:
碩士國立臺中技術學院
事業經營研究所
94
Credit cards are a popular tool for transactions in many countries lately. However, credit card frauds have occurred frequently. How to detect credit card frauds, therefore, has become a key issue in recent years. Many previous studies proposed models which were constructed from the past real transaction data of many others to detect new transactions of a certain individual. In contrast to those traditional approaches, this study employs a personalized approach to solve the problem of credit card fraud. The personalized approach proposes to prevent fraud before the consumer uses a credit card or when the collected data are few. This new approach is promising. However, there are still some problems which have to be solved. For examples, 1) consumers are not willing to spend too much time to answer questions so that the collected data are few, 2) the dynamic consumer behavior may cause data overlapping. To improve the problems mentioned above, this research employs the personalized approach to address the credit card fraud problem. The main purpose of this study is to investigate the influences of data distribution on the prediction accuracy. Support vector machine (SVM), back propagation network (BPN), and binary support vector system (BSVS) are used to construct detection models for credit card fraud. The experimental results show that SVM and BPN can obtain good training results. However, both techniques fail to predict future data accurately for those cases with high training results. Besides, the classification results of these three classifiers are comparable. Compared to the other two techniques, BSVS is the easiest tool to use. This study also employs several techniques, such as hierarchical SVM, majority voting, and over-sampling, to improve true negative rates. Results from the experiments indicate that these techniques can increase true negative rates effectively.
35
Yeh, Shu-Wan, and 葉淑婉. "Risk Bearing in Credit Card Fraud -- The Case of Lost or Stolen Cards." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/04439772527526539175.
Full textAbstract:
碩士逢甲大學
會計與財稅所
91
Abstract The money loss due to credit card fraud in Taiwan is more than three billion NT dollars from 2000.06 to 2001.06. These years the number of suits about credit card fraud also skyrockets. Risk bearing is about the key issue in these suits. We discuss risk bearing in credit card fraud and focus on the case of lost or stolen cards. The liability in credit card fraud, likes product liability, located on the border between contract and tort. Here we use economic theories of contract and tort analyzing efficient risk bearing in credit card fraud. That means the way we allocate risk should give both the credit card holders and issuers the incentive to take all efficient precautions. In Taiwan, the risk bearer of lost or stolen credit card was first the credit card holders but now card issuers. We find that the evolution of standard form contract of credit card responded to the verdicts of the court. However, the card holders now have no incentive to prevent the credit card fraud. We suggest that the rule of risk bearing in credit card fraud should be “Strict Liability with Contributory Negligence”, where the card issuers bear the risk unless the card holders are proved negligent.
36
Yeh, Ching Hsin, and 葉慶信. "A Fraud detection model in the credit card risk management process." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/89213878242171813466.
Full textAbstract:
碩士國立政治大學
管理碩士學程(AMBA)
96
The fraud of credit card usage has caused significant losses in worldwide issuing banks. The fraud syndicates have developed cross-boarder fraudulent activities along with global patners, which not only impacts worldwide economy, but also challenges the strategies initiated by all issuers. Due to the sophistication of the credit card process, experienced people and informative message are required elements to optimize the fraud detection process. The study attempts to analyze those major factors effecting credit card fraud detection process by adapting empirical analysis method on two real cases. Major findings are: 1) under a careful cost and benefit calculation, the more the SMS message sending, the higher the fraud detection rate, 2) the more the experience of detectors, the more effective the performance of the detection, and 3) the more the information shared across issuing banks, the higher the detection rate achieved for fraud skimming. In addition to the optimization of current fraud detection operation, the study is planned to draw public's attention on the serious credit card fraud issue. It is hoped that the attack level of credit card fraud could be mitigated effectively by taking recommendations made by this study.
37
Dolo, Kgaugelo Moses. "Differential evolution technique on weighted voting stacking ensemble method for credit card fraud detection." Diss., 2019. http://hdl.handle.net/10500/26758.
Full textAbstract:
Differential Evolution is an optimization technique of stochastic search for a population-based vector, which is powerful and efficient over a continuous space for solving differentiable and non-linear optimization problems. Weighted voting stacking ensemble method is an important technique that combines various classifier models. However, selecting the appropriate weights of classifier models for the correct
classification of transactions is a problem. This research study is therefore aimed at exploring whether the Differential Evolution optimization method is a good approach for defining the weighting function. Manual and random selection of weights for voting credit card transactions has previously been carried out. However, a large number of fraudulent transactions were not detected by the classifier models. Which means that a technique to overcome the weaknesses of the classifier models is required. Thus, the problem of selecting the
appropriate weights was viewed as the problem of weights optimization in this study. The dataset was downloaded from the Kaggle competition data repository. Various machine learning algorithms were used to weight vote a class of transaction. The differential evolution optimization techniques was used as a weighting function. In
addition, the Synthetic Minority Oversampling Technique (SMOTE) and Safe Level Synthetic Minority Oversampling Technique (SL-SMOTE) oversampling algorithms were modified to preserve the definition of SMOTE while improving the performance. Result generated from this research study showed that the Differential Evolution
Optimization method is a good weighting function, which can be adopted as a systematic weight function for weight voting stacking ensemble method of various classification methods.School of Computing
M. Sc. (Computing)
38
Hsu, Chih-Hsueh, and 許致學. "Decision support system of finding celluar phone short message rules for preventing credit card fraud." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/91253671341563844055.
Full text
39
Budhram, Trevor. "Examining the unique security features of a credit card with the aim of identifying possible fraudulent use." Diss., 2007. http://hdl.handle.net/10500/631.
Full textAbstract:
The use of credit cards has become a way of life in many parts of the world. Credit cards have also created many new opportunities for criminal activity.
It is in this light that organizations such as VISA International have explored a variety of security alternatives by constantly reviewing security measures that may be applied to cards and devote considerable resources to the maintenance of security systems and programmes. These programmes mandated by the association, include uniform card standards, security standards for manufactures, embossing and encoding of cards, standards for mailing the cards and credit background investigations of applicants. These standards assist investigators in examining counterfeit cards and distinguish a counterfeit card from a genuine card. The constant reviewing of security features and methods by the association is to create a card that is technically difficult to alter or counterfeit.Criminology
M.Tech. (Forensic Investigation)
40
Ferreira, Gerda. "Counterfeit card fraud : is there a need to introduce legislation to facilitate the prosecution of related criminal activities?" Thesis, 2012. http://hdl.handle.net/10210/8115.
Full textAbstract:
LL.M.Despite payment cards being of a fairly recent origin,1 these instruments of payment play an increasingly significant role in commerce. With reference to credit cards, Cornelius already in 2003 stated: “They fulfil various functions that are increasingly important at a time that ecommerce is taking off at a tremendous pace.”2 Similarly criminals continuously use more inventive and technologically advanced methods to commit fraud, including counterfeit card fraud. Is the South African criminal law, however, keeping up? The aim of this study is to investigate whether the various activities which form part of the criminal business value chain relating to counterfeit card fraud, with specific reference to bank payment cards, are sufficiently criminalised in South Africa or whether the inability of our criminal law to address the challenges posed by this crime type necessitates the introduction of further legislation. In the first part of the dissertation the South African common and statutory criminal law is investigated in some depth to establish the applicability thereof on the activities forming part of the criminal business value chain relevant to counterfeit card fraud. The appropriateness of certain statutory provisions is questioned and recommendations are made to amend current legislation. An argument is also advanced for further development of the common-law offence of theft to include identity theft and the unlawful copying and subsequent use of data. Brief reference is made to the international situation. Chapter 2 is an introduction to bank payment card fraud in South Africa focusing on the most prevalent forms thereof being card-not-present fraud and counterfeit card fraud. Reference is made to the manner in which offences related to counterfeit card fraud are currently approached in our criminal courts and the limited impact prosecutions has on the prevalence of this fraud type.
41
Geldenhuys, Nicolaas D. C. "An evaluation of identification methods used in the investigation of counterfeit card fraud." Diss., 2016. http://hdl.handle.net/10500/21185.
Full textAbstract:
Today, the use of one's bank card to pay or withdraw money is common. Modern technology provides us with the convenience of instant transactions at the automated teller machine or point of sale but unfortunately, it has also brought the reality and risk of card skimming and counterfeit card fraud. Criminals have become very efficient and technologically advanced in skimming and counterfeiting cards, to such an extent that counterfeit card fraud has become a significant threat to the public, banking, retail and business in South Africa.
Counterfeit card fraud is a complex, multi-faceted crime, requiring specific skills and knowledge of card counterfeiting methods from police and bank investigators. The scope of its investigation is wide. It includes different crime scenes and offenders, sophisticated equipment and various aspects that need to be identified positively. Investigators find it difficult to identify perpetrators and certain aspects unique to this crime and, as a result, many investigations are unsuccessful. This research endeavours to establish what identification methods are available to investigators and which are effective.Police Practice
M. Tech. (Forensic Investigation)
42
Yin, Pei-Ling, and 殷珮玲. "Detecting Fraud Transactions of Credit Cards via Data Mining." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/66983734860531822426.
Full textAbstract:
碩士大同大學
資訊經營學系(所)
104
This paper proposes an approach to detect credit card fraud transactions problem due to online credit card transaction volume increased year by year, consumers often shop at the store site, credit card fraud, fraudulent network model has changed, poor existing expert rules to detect the effect of the present study was to construct a decision tree using detection rules to detect electrons business fraudulent transactions, including online shopping help "non-face-to-face" type of fraudulent transactions detected.
43
Jung, Huang Bo, and 黃博忠. "Using Mining Techniques to Detect Fraud Transactions with Credit Cards." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/05230273637804889037.
Full textAbstract:
碩士南台科技大學
資訊管理系
93
Credit cards have become one of the most popular tools when consumers pay the bills with the convenience and rapid development of credit cards. In the situation, the cases of defalcating credit cards increase rapidly. How to detect the abnormality at once has become one of the important problems that the Center of Credit Card has to think carefully when consumers use credit cards. In the study, the mining information is form the consumers’ deal. Each information includes the product items they purchased. The credit cards which consumers always use are mining target. We take mining techniques to detect whether the use of credit card is abnormality or not. According to the relativity and plurality of product items which consumers purchase, we mentione two steps for mining method to judge whether the use of credit card is abnormality or not. In the first step, we map the product items which use the credit card to purchase and the deal information of the credit card holder. If it adapts minimum support of transaction, we will judge that the consumption of the credit card is abnormality. If it doesn’t adapt minimum support of transaction, we will take the second step. In the second step, we take Classification to find out that those product items affect the will of using credit cards to purchase. We define that these products are related factors. Then from the deal information of credit card holders, we judge whether the related factors appear in deal information. If they are in it, the consumption of the credit card is normality. Otherwise, it is abnormality. The mining information is taken form the consumers’ deal. Each information includes the product items they purchased. The credit cards which consumers always use are mining target. We take mining techniques to detect whether the use of credit card is abnormality or not. According to the relativity and plurality of product items which consumers purchase, we mention two steps for mining method to judge whether the use of credit card is abnormality or not. In the first step, we map the product items which use the credit card to purchase and the deal information of the credit card holder. If it adapts minimum support of transaction, we will judge that the consumption of the credit card is abnormality. If it doesn’t adapt minimum support of transaction, we will take the second step. In the second step, we will administer the products one by one. According to the Decision Tree built by ID3 Operation, we can find out which factors will affect the will of purchasing. We define that these factors are related factors and count the proportion of related factors in the deal information. If it adapts minimum relation of single item, it will show that the consumption of the credit card is abnormality. In the same reason, we take the same method to administer other product items that he purchased and then count each single item. It will show the proportion of normality. If it adapts minimum relation of single item, it will show that the consumption of the credit card is normality. Otherwise, it is abnormality. According to the methods we mention, we can design and establish a detective system of credit cards. The mining result can provide the Center of Credit Card very useful information to supervise whether the consumption of the credit card is abnormality or not.
44
邱崇兼. "Using Clustering Techniques to Mine Fraud Transactions with Credit Cards." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/85151522419411801021.
Full textAbstract:
碩士南台科技大學
資訊管理系
92
With the fast growth of credit card, the credit card has become one of the most popular payment tools with consumer, but cause the deception case of embezzled credit card to increases rapidly. How detect consumer’s credit card transaction immediately whether fraud or not, has become one of the important problem which the credit card processing organization have to consider. In this thesis, we use data mining technique to detect credit card transactions whether fraud or not. We use consumer’s previous transaction data as mining data source, and use certain consumer’s current transaction data as mining target. According to the repetition and correlation of consumer’s purchased product, we develop a method which contains two stages to detect credit cards for consuming whether fraud or not. First, we compare the detected transaction data with the detected consumer’s previous transaction data. If the result satisfy minimum transaction similarity, then the transaction is judged normal. If the result does not satisfy minimum transaction similarity, then the detecting process has to use the method of second stage. In second stage, we design different clustering methods to mine certain consumer’s credit card data whether fraud or not. According to our method, we design and build a system to detect credit card transaction, and the result can be used as the assistance tool of credit card processing organization to monitor fraud transactions.
45
Lee, Yu-Chi, and 李育琪. "Research On Types Of Credit Cards Fraud—Focus on the Legal Institution In Mainland China." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/86674028527977949013.
Full textAbstract:
碩士東吳大學
法律學系
98
People use credit card since twentieth century, which become the mostly popular e-payment tool around the world other than cash till now. In spite of credit card is a very convenient and great benefit method, otherwise the related crime rate is rising and the types of criminal are diversifying. With high development of science, the technology of forging credit card is precision continuously, hence credit card fraud cases and damages increased abruptly, which not only create the risks of fraud and personal information leaking, but also make the banks to spend quite a few time and money to try to control and prevent it. The damage unrecoverable will to be bad debt allowance, further undertaken by the society to harmful influence the domestic economy. Despite where the credit card fraud happened, to improve the credit card’s defect of utilizing easily to commit crimes in addition to integral management by the bank of the whole link in credit card issuing including it’s customers, it is necessary and important to complete the finance manage regulations and standard of credit card fraud in criminal laws. Due to credit card fraud case is global and international crime, the Government in Mainland China（the People’s Republic of China）is facing the dilemma of an increased in credit card crimes and rampant criminal gangs as well. In view of the aspect of this research will discuss stipulations related to credit card crime in Criminal Law of P.R.C., it starts to introduce the credit card’s business transaction parties and system, to analyze types, characteristics, trend of fraud and the present situation of credit card business. After referring to the other legislations worldwide and the common emphasis, this research will try to assay and compare to the related provisions of P.R.C.. Finally, it suggests probable amending directions of laws and developing the strategy of precaution, including in R.O.C. and P.R.C., hopes to strengthen to protect great benefit with respect to everyone, society even the whole nation.