Credit Card Companies Research Articles

HOW EQUATED MONTHLY INSTALMENT (EMI) SCHEMES AND BUY NOW, PAY LATER (BNPL) SERVICES FUEL IMPULSIVE BUYING: A CLOSER LOOK AT CONSUMER BEHAVIOUR

An Equated Monthly Instalment (EMI) is a fixed payment amount made by a borrower to a lender at a specified date each calendar month. The EMI consists of both the principal amount and the interest on the loan, which is spread over a predetermined period. EMIs are commonly used in home loans, personal loans, and auto loans, where the borrower repays the loan in regular instalments over time. Credit card companies typically offer this facility, but nowadays, it is also available with debit cards. Many banks are now providing a pre-approved credit limit for their debit card holders as well. BNPL stands for "Buy Now, Pay Later". It is a payment option that allows consumers to purchase goods and services and pay for them later, typically with no interest or fees. BNPL schemes offer customers the convenience of paying for purchases over time, without needing a credit card or traditional loan. This payment option has become increasingly popular among consumers, particularly among younger generations, to manage their finances and make larger purchases more affordable. However, it also has potential drawbacks, such as higher spending and risks of missed payments, that should be considered before utilizing this payment option. The objective of this study is to examine the factors that motivate consumers to choose EMI schemes and BNPL services as payment options, and to evaluate their perceived advantages and the risks associated with them. The study primarily relied on primary data collected from 100 samples using convenient sampling, along with secondary sources such as published research reports on BNPL.

CREDIT CARD FRAUD DETECTION

It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. In an era where digital transactions have become ubiquitous, the security of financial transactions is of paramount importance. The advent of machine learning and data science techniques offers promising avenues for enhancing fraud detection mechanisms. Analysing a dataset is a critical step in obtaining relevant insights from massive amounts of data. This research paper delves into the use case of Data science & Machine Learning and its applications for our major project. It goes into the use of Python as a powerful tool for data analysis, emphasizing its importance in dealing with complex datasets. Furthermore, the project investigates the many Python libraries used in data science and machine learning applications, the significance of data visualization with Libraries such as Seaborn and Matplotlib, etc. After which it goes on with the main work. This project of ours delves into the realm of credit card fraud detection, leveraging Python and its powerful libraries such as NumPy, Pandas, Seaborn, TensorFlow, and Matplotlib for comprehensive data analysis and visualization. Employing a host of machine learning algorithms including K-Nearest Neighbors, Logistic Regression, Random Forest, Decision Tree, and LDA, the project aims to tackle the challenge posed by highly unbalanced datasets, specifically transactions made by European cardholders in September 2013. By discerning fraudulent transactions accurately, this endeavour seeks to bolster the integrity of financial systems, safeguarding both customers and institutions from potential losses. Keywords: Python, pandas, seaborn, data science, machine learning.

Helping consumers weather the storm: the impact of consumer-targeted resiliency programs on firm value

PurposeWith the goal of helping consumers bounce back from the financial challenges they faced as a result of the COVID-19 pandemic, many firms developed and announced consumer-targeted resiliency programs (e.g. Walgreens waived delivery fees, Associated Bank allowed deferred mortgage payments). However, there is a paucity of research examining the unique features of these programs, and whether firms' investors (the first external stakeholder group to provide them with feedback regarding their strategies) were receptive to these programs during a period of time in which firms themselves were suffering financially. Drawing on resilience theory and stakeholder theory, the present research incorporates an event study of consumer-targeted resiliency program announcements to understand their financial implications for firms, and to learn whether firms witnessed different financial effects as a result of firm- and program-specific factors.Design/methodology/approachThis study referred to business news publications and newswire services to collect a comprehensive list of consumer-targeted resiliency programs announced by publicly traded U.S. firms during the pandemic. The resulting dataset consisted of 145 announcements made during the period of February–June 2020. An event study was conducted in order to precisely measure the main effect of consumer-targeted resiliency programs on firm value, as manifested through abnormal stock returns. Finally, a moderation analysis (regression) was conducted to uncover whether firm characteristics or specific features of firms' consumer-targeted resiliency programs lead certain firms to witness stronger financial effects than others.FindingsThe main effect of consumer-targeted resiliency programs on firm value was found to be positive – a 1.9% increase on average. The moderation analysis finds that non-financial firms were rewarded more positively than financial firms (e.g. banks and credit card companies). In addition, financial aid (i.e. allowing customers to defer their payments to a firm for its products/services, versus a reduction in the price of a product/service or offering it for free or giving cash back to customers) and temporal characteristics (i.e. an offer being framed as limited-time, vs being indefinite or for the foreseeable future) are not found to have a moderating effect.Originality/valueThis theory-driven empirical study uncovers practical implications for managers of firms interested in whether investing in corporate social responsibility during times of crisis is a wise allocation of resources. Any form of financial aid for consumers, regardless of temporal limitations, is received positively by investors.

Small money, large profits: how the cashless revolution aggravates social inequality

Abstract The replacement of cash by cashless alternatives carries huge potential to aggravate social inequality. Governments struggle to manage these dynamics since they must keep a delicate balance between the formation of strong players and the provision of inclusive payment options. Studying the political economy behind the payment industry is crucial to understanding how digitalization has transformed payments. To this aim, we look at the history of the payment industry in two cases: the USA and the euro area. In the USA, the cashless revolution gave rise to an oligopoly of two extremely successful credit card companies, which, however, resulted in a banking system that does not serve the needs of at least one-fifth of the population. In the euro area, the population has access to affordable financial services; however, neither the private nor the public sector has been able to provide the infrastructure to integrate European payments.

“Screaming into the Void”: Canadians’ Experiences Reporting Identity Theft

More victims of identity theft report to private institutions, such as credit card companies and banks, than to law enforcement. Internationally, fraud victims have experienced difficulty receiving assistance from institutions, yet little research has examined the outcomes of identity theft and fraud victims in North America. This article presents findings about Canadian victims’ experiences reporting identity theft, drawn from 20 interviews with victims of identity theft in Ontario. Although some victims had positive experiences with institutions and were assisted promptly, many were let down: Some had to hound for help or were transferred repeatedly, while others felt no closure or that the process of reporting was unclear. Moreover, victims’ experiences varied even when characteristics of the identity theft incidents appeared similar, such as the type of fraud experienced and the number of accounts misused. This article closes by discussing the implications of these findings in the context of victim assistance.

Root cause analysis of credit card fraud

Fraud detection has always been a major problem in society, especially in the banking, insurance and medical sectors. As more and more people are using credit cards to pay, the fraud rates tend to get higher. This situation is a considerable risk for the credit card company. At the same time, credit cards and their related industries have become an indispensable part of the economic construction of various countries. Therefore through descriptive analysis, regression and factor analysis, this paper analyzes the root cause of fraudulent transactions and makes simple predictions. Discusses the characteristics of cardholders and influencing factors of fraudulent transactions, The subjective psychological factors have the biggest influence on fraudulent transactions and puts forward some suggestions to prevent fraudulent transactions.

Credit Card Fraud Detection Using Autoencoder & Decoder ML

Abstract: In recent years credit card fraud has become one of the growing problems. It is vital that credit card companies can identify fraudulent credit card transactions, so that customers are not charged for the items that they did not purchase. The reputation of companies will heavily damage and endangered among the customers due to fraud in financial transactions The fraud detection techniques were increasing to improve accuracy to identify the fraudulent transactions. This project intends to build an unsupervised fraud detection method using autoencoder. An Autoencoder with four hidden layers which has been trained and tested with a dataset containing a European cardholder transaction that occurred in two days with 284,807 transactions from September 2013

The no surcharge rule and its welfare implication

This paper investigates the welfare implications of banning the no surcharge rule (NSR) in credit card markets. Conventional wisdom indicates that banning the NSR may increase or decrease social welfare. This paper finds that lifting the NSR unambiguously decreases social welfare in a closed system and in an open system when Visa and MasterCard privatize. In a closed system, the unambiguous welfare implication is due to the fact that the distortion of Merchant internalization (MI) fully offsets the distortion of market power, and the monopolistic credit card company acts as a social welfare maximizer when it maximizes its own profit. The credit card service is always optimally provided under the NSR, and lifting it, which eliminates the distortion of MI, always leads to an under-provision of credit card service and a decrease of social welfare. In an open system, the credit card service is always under provided under the NSR, because the market power of issuing banks works as another distortion in addition to those in a closed system. Banning the NSR will further drive down the card usage and social welfare decreases.

Impacts of Smoking Ban Policies on Billiard Hall Sales in South Korea Using Objective Sales Information of a Credit Card Company: Quasi-Experimental Study.

Smoking ban policies (SBPs) are potent health interventions and offer the potential to influence antismoking behavior. The Korean government completely prohibited smoking in indoor sports facilities, including billiard halls, since the government revised the National Health Promotion Act in December 2017. This study aimed to examine the impact of the SBP on the economic outcomes of indoor sports facilities, particularly billiard halls. This study used credit card sales data from the largest card company in South Korea. Data are from January 2017 to December 2018. Monthly sales data were examined across 23 administrative neighborhoods in Seoul, the capital city of South Korea. We conducted the interrupted time series model using the fixed effects model and the linear regression with panel-corrected standard errors (PCSE). The sales and transactions of billiard halls were not significantly changed after the introduction of the SBP in the full PCSE models. The R2 of the full PCSE model was 0.967 for sales and 0.981 for transactions. The introduction of the SBP did not result in substantial economic gains or losses in the sales of billiard halls. In addition to existing price-based policies, the enhanced SBP in public-use facilities, such as billiard halls, can have a positive synergistic effect on reducing smoking prevalence and preventing secondhand smoke. Health policy makers can actively expand the application of SBPs and make an effort to enhance social awareness regarding the necessity and benefits of public SBPs for both smokers and the owners of hospitality facilities.

Customer-based Recommendation Model for Next Merchant Recommendation

In the recommendation system of the credit card company, it is necessary to understand the customer patterns to predict a customer’s next merchant based on their histories. The data we want to model is much more complex and there are various patterns that customers choose. In such a situation, it is necessary to use an effective model that not only shows the relevance of the merchants, but also the relevance of the customers relative to these merchants. The proposed model aims to predict the next merchant for the customer. To improve prediction performance, we propose a novel model, called Customer-based Recommendation Model (CRM), to produce a more efficient representation of customers. For the next merchant recommendation system, we use a synthetic credit card usage dataset, BC’17. To demonstrate the applicability of the proposed model, we also apply it to the next item recommendation with another real-world transaction dataset, IJCAI’16.

The Second War Between the States: How the United States Became the World’s Best Tax Haven

Abstract We want government to help us prosper. For working people, prosperity requires employment and employment requires business. After World War II, most of the world was either devastated or underdeveloped leaving the United States without foreign competition. Local competition took its place. The States and local governments competed against one another on their natural resources, access to transportation, infrastructure, schools, and work force. These are the products of government spending. Some States did not have much to attract economic development. They created their own attributes instead. For example, right to work laws attracted companies that wanted to avoid unions and no usuary limits attracted credit card companies who wanted to charge high rates. Other States offered tax holidays. Move here and pay no tax for ten years. But saving money in taxes lost its appeal when other jurisdictions offered even more. Rather than build good sewage systems or roads for everyone, towns provided free infrastructure built to company specifications in addition to tax incentives. By the 1970s, firms learned that they could get States and localities to bid against one another. Each providing a package of bigger incentives. We can see the result of these races to the bottom in cities and towns that gave companies whatever they wanted only to find themselves with vacant factories and roads leading to nowhere. While the States were competing with one another, the rest of the world was emerging from war. Like the States, these countries wanted to help their citizens prosper. For those without natural resources or great infrastructure or educated workers, one alternative was to become a tax haven. A tax haven is the other side of a tax incentive. With tax incentives, a government gives up the right to tax in the hope that a firm's relocation will bring its citizens success. In a tax haven, a government hopes to improve its citizens’ fortune by helping a foreign taxpayer avoid another government’s taxes. Whether tax incentive or tax haven, in the end, the result is the same. The stakes get higher and higher. The companies and foreign taxpayers move from site to site. They take everything they can get and then convince another government to give more. Now a decade of investigative journalism shows that not only are the States in race to the bottom with their own tax revenues, but they are also transforming themselves into tax havens thus helping foreign taxpayers deplete their home countries’ revenues. This paper is a cautionary tale. It shows what makes the United States the world's favorite tax haven and examines what we can expect if this trend continues.

A cross-sectional study on factors affecting the intention to quit smoking among female call centre employees.

This study aims to describe smoking related characteristics among female call centre employees in South Korea and identify the factors influencing intention to quit smoking in the next 6 months. This is a cross-sectional study. An anonymous online survey was conducted at three call centres of credit card companies in South Korea. Female employees with at least 6 months of experience (n = 115) who were currently smoking were included in this study. Overall, 20% of participants intended to quit within 6 months. Female call centre employees find it most difficult to resist the urge to smoke in negative mood situations. Factors affecting the quit intention were higher educational status, previous quit attempts lower perceived risk of craving and higher social support. Measuring and monitoring craving as perceived risk and providing social support can be useful for designing smoking cessation interventions in this population.

Credit Card Customers' Data Visualization

Nowadays, there are many people who have credit cards, but the frequency of using them varies according to some personal factors, so many bank managers are worried because of the loss of some customers. Therefore, in this report, I have used a data set of 10,000 credit card holders' personal information and then selected and visualised this data. This will give a better understanding of the current cardholders and perhaps some banks or credit card companies can use the data to come up with effective solutions to recover some of their lost customers and find some potential credit card customers. According to the data analysis, it is not difficult to find that the current credit card users are mainly middle-age, with undergraduate degrees, and have an income below 40k dollars, with a total transfer amount between 2k-3k dollars or between 4k-5k dollars.

In their own words: deception detection by victims and near victims of fraud.

Research on deception detection has usually been executed in experimental settings in the laboratory. In contrast, the present research investigates deception detection by actual victims and near victims of fraud, as reported in their own words. Our study is based on a nationally representative survey of 11 types of (mostly) online fraud victimization (N = 2,864). We used qualitative information from actual victims and near victims on why they didn't fall for the fraud, or how, in hindsight, it could have been prevented. The main detection strategies mentioned by near victims (N = 958) were 1) fraud knowledge (69%): these near victims clearly recognized fraud. Other strategies related to fraud knowledge were: noticing mistakes (27.9%), rules and principles about safe conduct (11.7%), and personal knowledge (7.1%). A second type of strategy was distrust (26.1%). A third strategy was 'wise through experience' (1.6%). Finally, a limited number of respondents (7.8%) searched for additional information: they contacted other people (5.5%), sought information online (4%), contacted the fraudster (2.9%), contacted their bank or credit card company (2.2%), or contacted the police (0.2%). Using knowledge as a strategy decreases the probability of victimization by a factor of 0.43. In contrast, all other strategies increased the likelihood of victimization by a factor of 1.6 or more. Strategies generally were uncorrelated, several strategies differed by type of fraud. About 40% of the actual victims (N = 243) believed that their victimization might have been prevented by: 1) seeking information (25.2%), 2) paying more attention (18.9%), 3) a third party doing something (16.2%), 4) following safety rules or principles, like using a safer way of paying or trading (14.4%), or by 5) 'simply not going along with it' (10.8%). Most of these strategies were associated with a higher, not lower, likelihood of victimization. Clearly, knowledge of fraud is the best strategy to avoid fraud victimization. Therefore, a more proactive approach is needed to inform the public about fraud and attackers' modus operandi, so that potential victims already have knowledge of fraud upon encountering it. Just providing information online will not suffice to protect online users.

Credit Card Fraud Detection using Machine Learning

Evolving technologies make human life easier with increasing challenges. Online payments have become an integral part of our lives in the era of digitalization. The credit card payment system has made transactions hassle-free. This led to E-Commerce appraisal. Digitalization of transactions has given rise to new forms of fraud and cyberattacks that can affect individuals and organizations. This had set hackers at a great deal to steal the cardholder details using different schemes. Credit card companies must recognize these fraudulent transactions at the earliest to retain credibility among the stakeholders. Traditional methods of fraud detection have proven ineffective in identifying and preventing these fraudulent activities and cyberattacks in real time. This paper discusses various Machine Learning algorithms that predict fraudulent transactions in real-time. Fraudulent activities are solved using data science and machine learning techniques with substantial processing power and the capacity to manage massive datasets. The model is trained on large volumes of the dataset. This paper emphasizes comparison of various machine learning algorithms' performance over the input. The accuracy and efficiency of several machine learning algorithms are measured and analyzed through tabulation and comparison. The trained model is integrated with a website to categorize financial transactions as either legitimate or fraudulent. On utilizing advanced machine learning algorithms, credit card fraud detection systems have become more refined and accurate in recent years. As a result, financial organizations and customers are protected against such fraudulent activities, leading to increased trust and confidence in utilization credit card payments.

How does the price structure of two-sided markets affect transaction volume and market share: evidence from the Korean credit card market

This study aims to empirically examine the impact of the price structure of two-sided markets on transaction volume and market share (MS) in the context of the Korean credit card industry. The Korean credit card market differs from those in the United States (U.S.) or Europe in terms of transaction structure (i.e. a three-party system in Korea vs a four-party system in the U.S. or Europe) and government policy. In addition to the merchant discount rate and the cardholder annual membership fee rate, the authors included and analyzed exogenous variables to eliminate any endogeneity. Based on the analysis results, the authors found that credit card usage performance (i.e. transaction volume) increases with an increase in the relative price ratio (merchant discount rate ÷ cardholder membership fee rate) paid by merchants and cardholders, provided that the total price (merchant discount rate + cardholder membership fee rate) paid by merchants and cardholders remains constant. Therefore, this study is the first to confirm that the Korean credit card market operated as the theoretical mechanism of a two-sided market during the analysis period. This effect can only be observed in specific cases such as the launch of the so-called “Chief Executive Officer(CEO)-designed card.” When a new CEO takes office in a credit card company and launches a “CEO-designed card,” there is a significant increase in not only card usage performance but MS as well owing to the price structure changes caused by expanding the benefits that customers derive from card use.

Unbalanced Credit Card Fraud Detection Data: A Machine Learning-Oriented Comparative Study of Balancing Techniques

The number of individuals who use credit cards has increased dramatically in recent decades, as has the volume of credit card fraud transactions. Consequently, banks and credit card companies must be able to classify fraudulent credit card transactions so that clients do not have to pay for products they did not purchase. Data Science can easily tackle such challenges, and the value of Machine Learning methodologies cannot be emphasized. The study demonstrates how to model utilizing multiple classifiers and data balance using machine learning approaches to learning about Credit Card Fraud Detection. The data has been observed as an imbalanced dataset that could have inferred not much optimal performance of models. The experimentation on the imbalanced data has been done and observed that XGBoost has yielded good performance with 0.91 precision score and 0.99 accuracy score. The different sampling techniques have been carried out in procedure so as to enhance the scores in terms of precision, recall, f1-score, and accuracy. The Random Oversampling technique has come out to be the best suited technique over the imbalance data and yields 0.99 precision and 0.99 accuracy score, when applied on the best model i.e., XGBoost.The models are then used to compare the results of all of the classifiers employed, resulting in varied conclusions and further research. While working on the study, many data balancing procedures such as oversampling, under sampling, and SMOTE are used, with XGBoost beating residual algorithms with a 99% accuracy score and precision score when Random Over-Sampling is considered. The research suggested the use of data sampling techniques to balance data over the algorithms that show best results under the imbalanced data scenarios, to conclude the best possible performance of the model for fraudulent activities classification.

Time-Weighted Cumulative LSTM Method Using Log Data for Predicting Credit Card Customer Turnover

One of the most important challenges for credit card companies is to retain customers. To achieve this, they predict whether customers will use credit cards and respond preemptively through marketing. Improper prediction leads to an increase in marketing costs; therefore, improving the performance of the prediction model is an important challenge for credit card companies. Therefore, credit card companies are working toward increasing the predictive power of the model, but the data used for learning are limited to formal data, such as card payment data; the log history stored on the application is not used. Prediction models using sequence data, such as log history, are being studied. However, no studies so far have appropriately utilized card payment data, log history, and information on the timing of the elements constituting the sequence. In this paper, we propose a method for predicting credit card turnover using application log and credit card payment data. The method embeds log data and weights each log using a term-weighting function. In addition, the time difference between the day customers visit the app and the last day of the month in which they leave is calculated. The weight value is higher when the timespan is shorter. The weighted log data were trained with a 2-layer LSTM model and its output layer was combined with the output layer trained with the card payment data for customer turnover prediction. It was verified that the model presented in this paper had a higher performance than the model using only card payment data and the model using only a time-weighted log sequence.

Automation of Credit Card Customer Churn Analysis using Hybrid Machine Learning Models

Credit Card Customer Churn Analysis (C4A) is a phenomenon where customers stop using a specific business credit card service. Predicting customer churn is crucial for Credit Card (CC) companies because it enables them to spot at-risk customers and take precautions to retain them. The aim of the paper named C4A is to create a model that accurately predicts customers who are most likely to stop using CC. The paper involves gathering and analyzing customer information from Kaggle, including transaction history, demographics and credit card usage patterns for prediction. Machine learning algorithms namely, Logistic Regression, KNN, XGBoost Classifier, Decision Tree and Hybrid Models integrating Logistic Regression and KNN, Logistic Regression and Decision Tree are used to train to find patterns and correlations that point to customer churn. The accuracy of the proposed method is 0.846 with LR, 0.849 with KNN, 0.90 with a hybrid model integrating LR and KNN, 0.928 by integrating LR and DT, 0.91 with DT, and 0.93 with XGBoost.

Credit Card Fraud Detection using Machine Learning and Data Science

Abstract: It is vital that credit card companies are able to identify fraudulent credit card transactions so that customers are not charged for items that they did not purchase. Such problems can be tackled with Data Science and its importance, along with Machine Learning, cannot be overstated. This project intends to illustrate the modelling of a data set using machine learning with Credit Card Fraud Detection. The Credit Card Fraud Detection Problem includes modelling past credit card transactions with the data of the ones that turned out to be fraud. This model is then used to recognize whether a new transaction is fraudulent or not. Our objective here is to detect 100% of the fraudulent transactions while minimizing the incorrect fraud classifications. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analysing and pre-processing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data.