Credit Card Fraud Detection Using Hidden Markov Model

The use of credit cards for electronic commerce purposes has been on the increase in recent time. Credit card being the most acceptable and popular mode of payment, the number of fraud cases associated with it is also on the rise. As a result of the extensive nature of credit card transaction details, it is challenging to identify fraud in a credit card system in recent years, which implies that the identification of credit cards' fraud accurately, quickly, and effectively is a gray area of research. In this article, an automated template-based credit cards' fraud prediction (CCFP) model is developed using dynamic time warping (DTW) technique. This proposed CCFP technique is novel, as it has not been previously used to predict fraud in credit cards' systems. The performance of this proposed DTW-CCFP model is verified using the dataset that contains the credit card transactions of European cardholders. In addition, the performance of this proposed DTW-CCFP model is compared with three different machine learning (ML) prediction models: logistic regression (LR), decision tree (DT) and random forest (RF). The results were documented using two different performance metrics: sensitivity and false discovery rate (FDR). The proposed DTW-CCFP model outperforms the LR, DT and RF techniques. Of interest, the proposed DTW-CCFP model achieves this feat using a small portion (less than 5%) of the dataset to build the template in comparison to the LR, DT and RF techniques, which uses between 20%-30% of the dataset for training to achieve a fairly reasonable result

This article discusses the concept of a credit card as a means of payment in Islamic law. There are two main problems studied, namely (1) the conception of Shariah credit cards (alternatives) in Sharia Banking that can accommodate the needs of the community that are appropriate and do not conflict with Islamic Sharia; (2) the opinion of the scholars regarding the use of credit cards. The two problems were studied using a library approach by using books, magazines, journals and several other scientific works as primary sources. After conducting research, the authors found that Islamic credit cards can only be accessed for transactions on goods that have been determined with halal criteria. There are several opinions of scholars regarding the law on the use of credit cards related to the problems above. There are scholars who allow and there are also those who forbid based on their respective foundations. The MUI National Sharia Council stated that the use of sharia credit cards is allowed as long as it fulfills the provisions, and if it violates these provisions, the law will become illegal.

Discriminating the number of credit cards held by college students using credit and money attitudes

Financial fraud is a serious threat that is expanding effects on the financial sector. The use of credit cards is growing as digitization and internet transactions advance daily. The most common issues in today's culture are credit card scams. This kind of fraud typically happens when someone uses someone else's credit card details. Credit card fraud detection uses transaction data attributes to identify credit card fraud, which can save significant financial losses and affluence the burden on the police. The detection of credit card fraud has three difficulties: uneven data, an abundance of unseen variables, and the selection of an appropriate threshold to improve the models' reliability. This study employs a modified Logistic Regression (LR) model to detect credit card fraud in order to get over the preceding difficulties. The dataset sampling strategy, variable choice, and detection methods employed all have a significant impact on the effectiveness of fraud detection in credit card transactions. The effectiveness of naive bayes, k-nearest neighbour, and logistic regression on highly skewed credit card fraud data is examined in this research. The accuracy of the logistic regression technique will be closer to 0.98%; with this accuracy, frauds may be easily detected. The fact that LR receives the highest classifier score illustrates how well LR predicts credit card theft.

Purpose: This study discussed the factors that influence the use and debt of credit cardholders in Jakarta and surrounding areas (Jakarta, Bogor, Depok, Tangerang, Bekasi) Research methodology: The dependent variable used in this study is the use of credit cards and debts on credit cards. This study's independent variables were demographic factors, credit card feature factors, and attitude towards money factors. The sample of this study was 333 respondents using the purposive sampling technique. The data analysis model used is Ordinary Least Square (OLS). Results: The results showed that there were influences from demographic factors (age, income, family size), features on credit cards (credit limits), and attitudes towards money (the main payment method with credit cards, card tenure) on the use of credit cards; also, demographic factors (gender, type of work, level of education, income) and attitude towards money (minimum payment) on credit card debt. Therefore the factors that banks need to consider to increase their income, and the government for control of public expenditure, also the public to pay more attention to spending on their credit cards so that there is no accumulation of debt that cannot be paid. Limitations: This study has several limitations of specifically only examines the people who are in Jakarta and their surroundings (Jabodetabek) and examines demographic factors, features on credit cards, and attitudes. Contribution: This study will examine demographic factors, features on cards, and attitudes towards money by uniting variables per category into a unified category. The indicators in this study are adjusted to the community in Indonesia. Keywords: Attitude towards money, Credit cards, Credit card features, Demographics

Nowadays, in the digital era, the use of credit cards is widespread. People buy and sell goods from home. E-commerce brings a boom to the lifestyle of the people, for the working family, it is a preferable tool to purchase and pay through online mode in order to save the time and visiting hours. However, with the increasing use of credit cards, there have also been a lot of cases of credit card frauds that augmented much in the corona period. Fake credit card transactions significantly affect financial institutions, banks, and clients, whereas fraudsters try to develop new ways of committing fraud daily. To avoid credit card fraud and maintain the credibility of our clients, we need to build a model for credit card detection. There are the various machine learning tools that can be applied in detection of such frauds, these tools can be used to design an enhanced model to detect credit card frauds efficiently. In this view, the study presents a feature selection technique approach of machine learning with different classifiers. The study proposed an optimization algorithm using ‘Firefly’ for feature selection with four different classifiers: neural network, k-nearest neighbors, Support Vector Machine, and decision tree. The performance of all these four classifiers is compared on the basis of accuracy parameter.

Over the past few decades, there has been a shift of people from using traditional payment methods to digital methods, thus creating innovation in the payment system. Nowadays, the market is determined to bring a different culture to Albania. The purpose of this study, which is based on the use of credit cards in the Albanian market, especially in Tirana, is to determine the attitude of society towards these credit cards. A questionnaire distributed among 100 consumers was used for primary data collection. This study contains both qualitative analysis and quantitative data analysis. The qualitative analysis addresses the ABC model of behavior, the use of credit cards, and the inflation problems caused by their use. The quantitative analysis highlights model statistics as well as the study of econometric analysis, based on the independent variables that are considered, such as monthly income level, security, prestige, and interest rate, which are thought to have a strong relationship with the use of credit cards as well as the expenses incurred during their use. Age, gender, monthly income, employment status, the reason for use, frequency of use per month, and duration of use are considered in the statistical model. Various tests have been developed to provide an accurate estimate of the relationship of variables using the SPSS Statistics program. All independent variables have exhibited a positive impact concerning the dependent variable. This paper aims to show the perceptions of people who use credit cards and those who hold a negative attitude about their use.

<strong>Abstract</strong> It is important to make payments contactless in order to comply with hygiene rules, especially when shopping under the new normal principles. It is expected that this will increase credit card use. Based on this, the aim of the study is to determine the demographic, economic and environmental factors affecting the use of credit cards. In this study, the data obtained from the Turkish Statistical Institute were used. Binary logistic regression and binary probit regression analyzes were used under discrete choice analysis to identify the factors affecting the household credit card use status. The analysis results showed that the factors such as gender, marital status, educational background, age, household size, employment status, income, expenditure, financial assets, saving, online shopping, and questionnaire year were effective on the credit card use attitudes of households. Determining the effects and effect sizes of these has contributed to explain the attitude of credit card use and has guided decision-makers and policymakers to transform the use of credit cards for contributing to the economy.

Credit card transactions have increased significantly every year. Along with the increasing use of credit cards, the risk of fraud by irresponsible people also increases. Credit card fraud can be detected with the help of machine learning. The main problem that often encountered is the transaction data has very large dimensions, unbalanced classes, and requires a detection process with a short computation time. Therefore we need a model that can produce good performance with short computation time using the support vector machine (SVM) method with grid search and genetic algorithm optimization. From the three models built, it was found that the SVM model using an initial dataset which was balanced using ADASYN and searching for the best parameters using grid search as a hyperparameter optimization technique was able to carry out good detection and short computing time. This model is able to detect fraudulent transactions with 99% sensitivity and 99% specificity and the shortest model training time among the other two models.

With the continuous development of the economy, the widespread use of credit cards shows a growing trend. However, simultaneously, the risk of credit card fraud still exists and cannot be ignored. This article utilizes bank card data for model training, with a particular focus on addressing the high dimensionality and imbalance of data in credit card transactions. In terms of model construction, it introduces a reinforcement learning-based Long Short-Term Memory (LSTM) network. Additionally, to improve the classification and recognition performance of the model, ensemble learning algorithms and convolutional neural networks are employed for enhancement. The research results indicate that, compared to other methods, the approach proposed in this article demonstrates a higher level of performance in the AUC (Area Under the Curve) metric of 0.92, effectively preventing financial risks, and providing a more reliable solution for credit card fraud detection. In conclusion, after comparing numerous models, it is evident that LSTM is an effective algorithm choice, particularly suitable for credit card fraud detection tasks.

The widespread use of credit cards has led to an increase in fraud. Credit card fraud detection involves identifying and preventing fraudulent transactions, either in real-time or post-occurrence. This paper seeks to create an advanced credit card fraud detection model via data mining. The proposed method comprises four essential steps: data acquisition, preprocessing, feature selection, and fraud detection. A recent balanced dataset is acquired, containing 28 anonymized features about the credit card transactions, along with the transaction amount and the transaction label (normal or fraud). The dataset is then explored to clean it and ensure its integrity. Feature selection is executed via the Energy Valley Optimization (EVO) metaheuristic method, employing the accuracy value of the Light Gradient Boosting Machine (LGBM) as the fitness function. This results in a 30% reduction in features. The reduced dataset is then input into the classification step, where an ensemble soft voting model is applied. This model encompasses Extra Trees, eXtreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) classifiers. The proposed model averages the probability of the three classifiers for each label and outputs the label with the highest average probability. The proposed method is assessed using recall, precision, accuracy, and F1-score, attaining 99.89%, 99.58%, 99.74%, and 99.74%, respectively. The proposed approach is evaluated against existing machine learning classifiers and relevant studies using the same dataset, showcasing enhanced performance and confirming its efficacy in identifying credit card fraud.

The current research examines influence of materialism and compulsive-buying behavior on Indian consumers’ credit card use. Research in Western countries posits that materialistic values and compulsiveness influence credit card use. However, results of the research differ from earlier researches. It suggests that Indian consumers’ credit card use is influenced by materialism but not by compulsiveness. Credit cards may be acquired to represent a lifestyle and improve individual’s status. The symbolic value associated with credit card is higher than its functional attributes. Consumers associate it with material possessions that bequeath status to them.

The development in the economic sector is influencing the development of banking products. One of the many products that is commonly used is credit card. In this context, The use of credit cards practically bring some problems that are reflected in the Islamic Law Perspective, especially because it does not specifically manage the credit cards according to Islam. It is different from the conventional credit cards that already have legal instruments clearly. Therefore, this study examines the legal implications in financing cards based on murabahah contract. This research is a normative legal research by analyzing the management of the Financing Card Based on Murabahah Contract. In order to help the analyses, this study uses the theory of Mаqаsid аl-syаri'аh and the theory of expediency (utility). The results that found related to the legal implications in financing cards based on murabahah contract can be reviewed from the relevancy to the theory of usefulness (utility). Credit cards as a modern means of payment, provide many conveniences and benefits in the midst of the rapid development of the business world. In addition, to address the use of credit cards based on usury, the Syariah Bank issued a Syariah Credit Card or Financing Card, this product must be based on the National Syariah Council Decision (Fatwa Majelis Ulama Indonesia) No.54 / DSN-MUI / 2006 on Syariah Card. Then in order to avoid legal implications that are not in accordance with syariah principles, from the aspect of the term that is used in Syariah, it is more appropriate to use the financing card term instead of credit card.

With increased internet usage, online transactions have been on the rise. One of the most prevalent problems faced is credit cards frauds. While web applications and mailing services are heavily spammed, the upsurge of handheld mobile devices has led to an outburst of heavy mobile credit card spamming. The matter is more severe in mobile devices due to lesser sophisticated filtering mechanisms in built in mobile operating systems. Recent advancements in electronic commerce and communication systems have significantly increased the use of credit cards for both online and regular transactions. However, there has been a steady rise in fraudulent credit card transactions, costing financial companies huge losses every year. The development of effective fraud detection algorithms is vital in minimizing these losses, but it is challenging because most credit card datasets are highly imbalanced. This work proposes a supervised machine learning algorithm to be trained to detect credit card frauds based on the Bayes Net with penalty based regularization. It is shown that the proposed approach attains higher classification accuracy compared to existing work. Keywords— Credit Card Fraud Detection, Machine Learning, Feature Selection, Imbalanced Datasets, Probabilistic Classifier, Classification Accuracy

Having unlimited needs and wants, humans as economic beings will struggle to meet their needs. In this modern era, shopping for human needs and desires has become easier to do with the availability of various stores and malls to online retail. This ease of shopping has increased interest in shopping for unlimited material needs and indulges Indonesians to continue making purchases in order to develop uncontrolled compulsive buying behavior. Therefore the authors aim to examine the effect of materialism on compulsive buying mediated by the use of credit cards and impulsive buying. The object of this research is credit card users in Batam. Sampling was done by giving a google form questionnaire to credit card users in the city of Batam. Demographic data of respondents were then analyzed using IBM SPSS Statistics version 25.0 and analysis of the effect of independent variables on the dependent variable was carried out using Smart PLS version 3.2.8. The results of this study indicate that the variables of materialism, use of credit cards and impulsive buying have a significant effect on compulsive buying .