Describing Coerced Debt Created in Abusive Marriages.

Credit card fraud is a common occurrence in today’s society because the majority of us use credit cards as a form of payment more frequently. This is the outcome of developments in technology and an increase in online transactions, which have given rise to frauds that have caused significant financial losses. In order to detect fraud in credit card transactions, efficient and effective approaches are needed. In this study, we developed a hybrid CNN‐SVM model for detecting fraud in credit card transactions. The effectiveness of our suggested hybrid CNN‐SVM model for detecting fraud in credit card transactions was tested using real‐world public credit card transaction data. The architecture of our hybrid CNN‐SVM model was developed by replacing the final output layer of the CNN model with an SVM classifier. The first classifier is a fully connected layer with softmax that is trained using an end‐to‐end approach, whereas the second classifier is a support vector machine that is piled on top by deleting the final fully connected and softmax layer. According to experimental results, our hybrid CNN‐SVM model produced classification performances with accuracy, precision, recall, F1‐score, and AUC of 91.08%, 90.50%, 90.34%, 90.41, and 91.05%, respectively.

This research used a Web-based survey of students at a Midwest regional university to measure the extent of credit card use by first-year students and seniors. The results indicate that the variables influencing credit card use and the carrying of a balance from one month to the next include the number of cards held by the student the student’s income !evel and the presence of educational loans. A significant number of surveyed students at both grade levels are affected by credit card debt but no specific type of purchases lead to carrying a balance. First-year students and seniors differed significantly in the number of cards they held the monthly balances they carried and the ways in which they acquired their cards. Those who acquired their credit cards through on-campus solicitation carried a substantially higher average monthly balance than those students acquiring the cards via other methods. The students~ involvement with their parents affected their card balance~ but knowledge of interest rates and types of transactions appeared to have no influence.

This study examines the association between self-employment, otherwise known as entrepreneurship, and student loan debt. Based on data from the 2021 National Financial Capability Study, which were analyzed using a multinomial probit model, our results suggest that households that used student loans to finance the education of one household member are more likely to report that the other member of the household pursued self-employment, with everything else remaining equal. This association between student loans and household self-employment is both economically and statistically significant. Our results highlight the importance of alternative forms of financing for entrepreneurship and expand upon existing knowledge about the unintended effects of student loans. Policymakers should consider these results when analyzing the various intended and unintended benefits of policies affecting the availability of student loans.

Although research on credit card debt in developed countries has identified predictors of debt among<br />college students, it is unknown whether these same predictors apply in emerging markets, such as<br />Brazil. To examine this issue, a total of 1257 college students, 814 from Brazil and 443 from the United<br />States, participated in a study exploring the utility of a theory of planned behavior as a predictor of<br />credit card debtand student loans among college students, as well as perceived financial well-being.<br />Compared to the Brazilian participants, the American sample was more financially self-confident,<br />reported better financial well-being, and was more likely to believe that credit cards are negative.<br />Similar predictors of financial well-being emerged in the samples. Specifically, parenting practices<br />related to money and better self-reported delay of gratification are related to more positive financial<br />attitudes and lower levels of debt. Although the debt to income ratio among card holders was similar,<br />Brazilian students held more credit cards than American students. Greater delay of gratification was<br />related to lower levels of student loans in the United States, but there were no significant predictors of<br />student loans in Brazil.

Are Finnish students prepared for the realities of the economic world? Will Finnish college students be buried under student loans and credit card debt? We surveyed Finnish college students (n=135) in the spring of 2016. We examined their use of student loans, credit cards, budgeting, and gambling. We found student loans were modestly used, gambling was almost nonexistent, and budgets were underutilized. However, we found Finnish students to be uninformed about financial tools such as credit cards. We conclude with discussing how to move into new subject areas with this pilot project.

Pattern identification of stock market moves or fraudulent credit card purchases have focused on the use of statistical and neural network techniques. This project for a major credit card encompassed these two techniques in the detection of fraudulent patterns of card holder activity. The results are reported. Fraud is a crime although there are variations in its definition among the statutes of various countries where the credit card is used. Fraud is subdivided into the following categories: lost, stolen, not received, counterfeit, fraudulent application, fraudulent use of card, and other. The focus of the study is the fraudulent use of the card. Specifically, the objectives of the study were to develop a scientific approach to risk pattern analysis and to initiate development projects which significantly increase the bank's ability to identify and control risky transaction patterns. The industry's fraud accounts for over two billion dollars in losses each year. Although fraud losses are high in absolute dollars, they are only a small proportion of total activity. Thus, the problem of risk pattern recognition can be characterized as looking for a large number of needles in an enormously large haystack. The data used in this study include actual transactions organized by account over a six month period. Fraudulent transactions are clearly identified. This allows one to segment the accounts into good and bad meaning those that had one or more fraudulent transactions. Over fifty million transactions were used in the analysis.

As dependency on credit cards and online transactions is increasing, the scope for unauthorized payments or fraudulent transactions is on the rise. Huge financial losses are borne by banks every year due to fraudulent transactions. The process of identifying such transactions among millions of transaction records can be perfected using machine learning models, even more so by ensembling them. This study takes a real-time financial dataset and analyzes the efficiency of various machine learning models in predicting fraudulent transactions. Individual ML models are also analysed, ensembled and tested on the dataset. Upon extensive analysis and research, it is concluded that an ensembled model of LightGBM, decision tree classifier and XGBoost gave the highest AuC score of 87%. Further, a user-interactive tool is also created, which predicts fraudulent transactions from real-time transactions. The tool makes use of the model with highest prediction efficiency and presents it in an interactive manner. This study and practical demonstration show advancement in prediction of fraudulent transactions when compared to existing ML models and its user-friendly software incorporation.KeywordsFraud detectionEnsembleAccuracyFraudulent transactionBankingMachine learning model

Emerging adults can experience conflicts with their dating partner, leading to intimate partner violence (IPV). In order to understand the vulnerability factors involved in IPV victimization, the current study explored a serial multiple mediation model to determine the links between parental attachment (to the father and mother), self-esteem, and social problem solving (SPS) on the three forms of IPV (psychological, physical and sexual). Based on an online survey, 756 emerging adults (84.8% women, mean age = 23.52) completed self-report questionnaires related to parental attachment, self-esteem, SPS (avoidance and impulsive/carelessness style), and IPV during the past year. The study design was cross-sectional and data were analyzed through partial least structural equation modeling (PLS-SEM) technique. The findings did not support serial multiple mediation model, as the indirect effects of the two specific mediation models were not significant. However, the total indirect effects were significant, indicating a cascade effect chain of events between the variables; insecure parental attachment was related to lower self-esteem, which was associated with poor SPS skills (especially impulsive/carelessness style), which in turn was associated with both psychological and physical violence victimization. The implications of the findings for promoting the life skills of emerging adults, such as problem solving or self-esteem, to enable them to handle their relationship conflicts are discussed.

This research is an empirical examination of the role of psychological characteristics of household decision makers in their borrowing decisions. Using a unique household survey data that ties together relevant concepts from the Survey of Consumer Finances (SCF) and psychological and attitudinal literature, we obtain direct measures of each surveyed household’s personality scores, relevant attitudes, and financial profiles. Following regression analysis, we examine the relationship between attitude towards borrowing and intentions to apply for specific borrowing options and inspect the role of personality traits in such decisions. Specifically, we focus on tow personality traits, the need for material resources and the need for arousal, which have been largely ignored in extant household finance literature. Our findings indicate that the attitude toward borrowing and the intention to borrow are not always consistent and, more interestingly, the discrepancies between the two vary across personalities, highlighting the role of personality traits in borrowing decisions. Specifically, while the positive relationship between attitude towards borrowing and intention to borrow is intuitive, we show that this relationship is trivial for individuals who score low on need for material resources and individuals with low degrees of need for arousal. In contrast, for individuals with higher levels of need for material resources and need for arousal, the positive association between attitude towards borrowing and the intention to borrow is significantly intensified. Further, our results suggest that borrowing options are not homogenous and are motivated differently. Consistent with the view that individuals with greater need for material resources consider quantity and quality of possessions as the criteria to judge personal success, we find that these individuals have stronger intentions for mort- gages, home improvement loans, business loans, personal loans, and payday loans. Similarly, consistent with the view that individuals with greater need for arousal favor stimulation and excitement that is often associated with more spending, we find that the borrowing decisions of these individual are marked with stronger intentions for home improvement loans, business loans, student loans, personal loans, and payday loans. The intentions for credits cards and automotive loans seem to be independent from the borrower’s personality. Finally, we report strong evidence that personal attitu- dinal biases towards money, risk, financial planning, and borrowing as well as certain demographic characteristics influence household’s borrowing behavior. Our work contributes to the literature on household finance in several ways. First, we focus on two under-researched personality traits to examine their roles in household borrowing decisions. Second, this research recognizes the distinction between the attitude towards borrowing and the intention to borrow and examines the inconsistencies between them. Third, we consider a wide spectrum of borrowing options that differ in terms of risk, motivation, and loan maturity.

Credit card is considered as one of the most popular paying methods for online and regular purchases, due to the advancement in communication and electronic commerce systems. Thus, the fraud associated with these transactions increased significantly. The great utilization of electronic payment is highly affected by this fraudulent transactions, which requires urgent detection to solve this issue. Therefore, effective and efficient approaches to detect fraud in credit card transactions are needed. To catch the fraudulent transaction, a good fitting model is needed, hence researchers recommends the use of various Machine Learning (ML) techniques, because of its beneficial characteristics. The main aim of the research work is to implement an ensemble based ML techniques for Credit Card Fraud Detection (CCFD). The strength of our model is a combination of the forces of the three subsystems; Recursive Feature Elimination (RFE), CCFD's using ensemble classifiers, and Synthetic Minority Oversampling (S MOTE) to deal with the problem of unbalanced data to identify the most effective prediction features. The proposed model run typical tests on two real databases of public credit card transactions, including fraudulent and official ones. Based on the comparison of other ML methods, the extra tree classifier has performed better and achieved high efficiencies such as 96% of accuracy and 57.95% of F1-measure.

With the rapid evolution of the technology, the world is turning to use credit cards instead of cash in their daily life, which opens the door to many new ways for fraudulent people to use these cards in a bad way. According to the Nilson report, global card losses are expected to exceed $35 billion by 2020. To ensure the safety of users for these credit cards, the credit card’s provider should provide a service to protect users from any risk they may face. Consequently, we present our approach to predict legitimate or fraud transactions on the IEEE-CIS Fraud Detection dataset provided by Kaggel. Our model is BiLSTM- MaxPooling-BiGRU-MaxPooling which based on bidirectional Long short-term memory (BiLSTM) and bidirectional Gated recurrent unit (BiGRU). We also applied six machine learning classifiers which are: Naïve base, Voting, Ada boosting, Random Forest, Decision Tree, and Logistic Regression. Comparing the results from machine learning classifiers and our model the results show that our model achieved better as we got 91.37% score.

The usage of credit cards for online purchases has increased exponentially and so has fraud. In recent years, detecting fraud in credit card transactions has become significantly more difficult. As a result, having effective and accurate methods for detecting fraud in credit card transactions is vital. Although supervised learning algorithms have been shown to be effective in detecting credit card fraud, they have not generated substantial results. Hence, a Deep Neural Network (DNN)-based technique is proposed. The sequential model is used to construct the proposed DNN. However, the parameters of the model, such as the number of nodes and the activation function in the hidden layers, can also have an impact on its output. The proposed technique was evaluated on a credit card transaction dataset that comprised fraudulent and genuine transactions. This technique obtained the accuracy, area under curve (AUC), and precision of 99.93%, 99.99%, and 99.89%, respectively. This technique was compared with various models such as Optimized LightGBM, Multilayer Perceptron (MLP), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM).

The existence of fraud in credit card transactions causes many financial losses leading to customers’ loss of trust. Fraud detection methods based on machine learning techniques prevent such losses. Despite the literature on fraud detection, there is a lack of algorithms that detect fraud with acceptable performance in the credit card fraud detection field. Therefore, this study proposed a comprehensive ensemble-based method using an efficient weighted voting strategy for credit card fraud detection that can address the previous algorithms’ weaknesses. First, since the dataset is imbalanced, the proposed method balanced the dataset by stratifying it into three different proportions of normal and fraudulent transactions (1 to 1, 1 to 4 and 1 to 9 ratios). The features in each dataset are ranked by four feature-ranking methods, and the Random Forest classifier is applied to each of them for selecting the essential features. Afterward, using the seven base classifiers and the chosen features, 12 ensembles have been developed. Besides, a weighted voting strategy is proposed, and the fraudulent transactions are detected through voting based on the base classifiers’ and ensembles’ weights, which are calculated by their performance. The computational results indicated that the suggested Eclf10 is the best ensemble and its Logistic Regression classifier also has the best performance among other base classifiers. The Eclf10 leads to 99.97% accuracy, 87.78% precision, 97.70% recall, 92.21% F1-score and 95.634% F2-score, which has a superiority over the previous ensemble-based methods (e.g. majority voting ensemble, stacking classifier, Adaboost, Gradient Boosting).

In this digital world, numerous credit card-based transactions take place all over the world. Concomitantly, gaps in process flows and technology result in many fraudulent transactions. Owing to the spurt in the number of reported fraudulent transactions, customers and credit card service providers incur significant financial and reputation losses respectively. Therefore, building a powerful fraud detection system is paramount. It is noteworthy that fraud detection datasets, by nature, are highly unbalanced. Consequently, almost all of the supervised classifiers, when built on the unbalanced datasets, yield high false negative rates. But, the extant oversampling methods while reducing the false negatives, increase the false positives. In this paper, we propose a novel data oversampling method using Generative Adversarial Network (GAN). We use GAN and its variant to generate synthetic data of fraudulent transactions. To evaluate the effectiveness of the proposed method, we employ machine learning classifiers on the data balanced by GAN. Our proposed GAN-based oversampling method simultaneously achieved high precision, F1-score and dramatic reduction in the count of false positives compared to the state-of-the-art synthetic data generation based oversampling methods such as Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN) and random oversampling. Moreover, an ablation study involving the oversampling based on the ensemble of SMOTE and GAN/WGAN generated datasets indicated that it is outperformed by the proposed methods in terms of F1 score and false positive count.

Due to the emigration of world business to the internet, credit ‎cards have become a tool for ‎payments for both online and outline purchases. However, fraudsters try ‎to attack those systems ‎using various techniques, and credit card fraud has become dangerous. To ‎secure credit cards, ‎different methods are proposed in the academic paper based on artificial ‎intelligence. The proposed ‎solution in this paper aims at combining the robustness of three methods: ‎the differential evolution ‎algorithm (DE) for selecting the best hyperparameters, a resampling ‎technique for handling ‎imbalanced data issues, and the XGBoost technique for classification. Finally, ‎the fraudulent ‎transactions are classified using the optimized XGBoost algorithm. The proposed ‎solution is ‎evaluated using two real-world datasets: the European dataset and the UCI dataset. The ‎evaluation ‎in terms of accuracy, sensitivity, specificity, precision, and F-measure shows the ability and ‎the ‎superiority of the proposed approach in comparison with the state-of-the-art machine learning ‎‎models.‎