Credit Card Transaction Data Research Articles

A Hybrid Convolutional Neural Network and Support Vector Machine‐Based Credit Card Fraud Detection Model

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.

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.

A Novel Approach for Credit Card Fraud Detection Using LR Method - Comparative Studies

Creditcard fraud detection mechanism is the most needed one in the present world. This is due to the development of e-commerce and online transaction. The main aim of this paper is to predict fraudulent transactions in a credit card transaction data set using statistical methods. Statistical methods based on Logistic Regression and Random Forest are developed and applied to credit card fraud detection problems. This work mainly focuses on machine learning algorithms as a classification model. The classification model is used for categorizing the dataset into fraud and non-fraudulent transactions. This project comprises methods for analyzing the fraud data to extract meaningful statistics and other characteristics of the data. The use of a model is to predict fraud with different statistical methods. This paper is one of the first to compare the performance of Logistic Regression and Random Forest methods in credit card fraud detection with a transaction data set using R. The results of the two algorithms are based on accuracy, precision, recall, and F1-score. The ROC curve is plotted based on the confusion matrix. The Random Forest and the Logistic Regression algorithms are compared and the algorithm that has the greatest accuracy, precision, recall, and F1 score is considered the best algorithm that is used to detect fraud.

A Novel Approach for Credit Card Fraud Detection Using LR Method - Comparative Studies

Creditcard fraud detection mechanism is the most needed one in the present world. This is due to the development of e-commerce and online transaction. The main aim of this paper is to predict fraudulent transactions in a credit card transaction data set using statistical methods. Statistical methods based on Logistic Regression and Random Forest are developed and applied to credit card fraud detection problems. This work mainly focuses on machine learning algorithms as a classification model. The classification model is used for categorizing the dataset into fraud and non-fraudulent transactions. This project comprises methods for analyzing the fraud data to extract meaningful statistics and other characteristics of the data. The use of a model is to predict fraud with different statistical methods. This paper is one of the first to compare the performance of Logistic Regression and Random Forest methods in credit card fraud detection with a transaction data set using R. The results of the two algorithms are based on accuracy, precision, recall, and F1-score. The ROC curve is plotted based on the confusion matrix. The Random Forest and the Logistic Regression algorithms are compared and the algorithm that has the greatest accuracy, precision, recall, and F1 score is considered the best algorithm that is used to detect fraud.

Machine Learning Methods for Credit Card Fraud Detection

Machine learning is an innovative and efficient tool to prevent credit card fraud, however, given the variety of machine learning models, which model is the most suitable for fraudulent transaction predictions becomes a tough question to answer. In this research, a comprehensive evaluation method is borrowed to compare performances between different machine learning models. More precisely, this research uses the Area under the ROC Curve (AUC) metric to evaluate and compare performances between four different machine learning models with the same transaction information dataset. The four models are K Nearest Neighbor, Logistic Regression, Random Forest, and Support Vector Machine. In this research, a dataset that contains over one million credit card transaction data is processed and divided into training data and testing data. After preprocessing, the same training data are fitted into four different models and being test against the same testing data. After a series of hyperparameter tuning, the AUC score of each model is obtained and compared. The comparison result indicates that Random Forest makes the most accurate and consistent predictions on fraudulent transactions in this dataset, and thus can be recommended as the primary machine learning algorithm to prevent credit card fraudulent transactions.

Hybridizing graph‐based Gaussian mixture model with machine learning for classification of fraudulent transactions

SummaryIt has been observed that a good number of financial organizations often face a number of threats due to credit card fraud that affects consistently to the card holder as well as the organizations. This is one of the fastest‐growing frauds of its kind and the most emerging problems for the institutions to prevent. A number of researchers and analysts have shown interest to work on this area in order to identify such issues in an effective manner by applying various supervised as well as unsupervised learning approaches. In this assessment, three classification techniques such as support vector machine (SVM), k‐nearest neighbor (k‐NN), and extreme learning machine (ELM) that come under supervised learning category are applied to the BankSim data to categorize the normal and fraudulent class transactions in credit card. These algorithms are incorporated with the graph features extracted from the dataset by using a database tool Neo4j. The nodes of the graph represent the transactional data samples and the edges create relationships among the nodes to find the patterns of data using connected data analysis. k‐fold cross validation approach in Gaussian mixture model (GMM) has been applied for classification of the credit card transaction data in a single distribution. Further, a combined graph‐based Gaussian mixture model (CGB‐GMM) has been proposed to effectively detect the fraudulent instances in credit card transactions with the application of graph algorithms such as degree centrality, LPA, page rank, and so forth. Each of the learning algorithms are implemented with and without the application of graph algorithms and their performances are assessed empirically for analysis.

Social Benefits and Private Costs of Driving Restriction Policies: The Impact of Madrid Central on Congestion, Pollution, and Consumer Spending

Abstract Low Emission Zones are defined areas within a city where driving restrictions are introduced with the aim to reduce pollution, but they may also unintentionally distort consumer spending decisions. By increasing transportation costs to ban-affected areas, driving restrictions could discourage spending in stores of those areas. This paper empirically evaluates the effects of a driving restriction regulation in Madrid, Spain, known as Madrid Central. First, using a difference-in-differences identification strategy, we find an immediate decrease of 19% in pollution and of 16% in congestion with pollution dropping further once fines were levied. Second, we rely on credit card transaction data to show consumers affected by the regulation reduced their brick-and-mortar spending in the regulated area by 21%. Finally, because affected consumers partially substitute their consumption spending from brick-and-mortar to online shopping, we find suggestive evidence that e-commerce may smooth the impact of changes in transportation costs due to environmental regulations.

Smart flood resilience: harnessing community-scale big data for predictive flood risk monitoring, rapid impact assessment, and situational awareness

Smart resilience is the beneficial result of the collision course of the fields of data science and urban resilience to flooding. The objective of this study is to propose and demonstrate a smart flood resilience framework that leverages heterogeneous community-scale big data and infrastructure sensor data to enhance predictive risk monitoring and situational awareness. The smart flood resilience framework focuses on four core capabilities that could be augmented by the use of heterogeneous community-scale big data and analytics techniques: (1) predictive flood risk mapping; (2) automated rapid impact assessment; (3) predictive infrastructure failure prediction and monitoring; and (4) smart situational awareness capabilities. We demonstrate the components of these core capabilities of the smart flood resilience framework in the context of the 2017 Hurricane Harvey in Harris County, Texas. First, we present the use of flood sensors for the prediction of floodwater overflow in channel networks and inundation of co-located road networks. Second, we discuss the use of social media and machine learning techniques for assessing the impacts of floods on communities and sensing emotion signals to examine societal impacts. Third, we describe the use of high-resolution traffic data in network-theoretic models for nowcasting of flood propagation on road networks and the disrupted access to critical facilities, such as hospitals. Fourth, we introduce how location-based and credit card transaction data were used in spatial analyses to proactively evaluate the recovery of communities and the impacts of floods on businesses. These analyses show that the significance of core capabilities of the smart flood resilience framework in helping emergency managers, city planners, public officials, responders, and volunteers to better cope with the impacts of catastrophic flooding events.

Credit Card Fraud Detection

Abstract: Now a day’s online transactions have become an important and necessary part of our lives. 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. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Such problems can be tackled with Machine Learning with its algorithms. 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 analyzing and preprocessing 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. Keywords: Credit Card, Python, Detection

Unveiling spatial patterns of disaster impacts and recovery using credit card transaction fluctuations

The objective of this study is to examine spatial patterns of disaster impacts and recovery of communities based on fluctuations in credit card transactions (CCTs). Such fluctuations could capture the collective effects of household impacts, disrupted accesses, and business closures and thus provide an integrative measure for examining disaster impacts and community recovery. Existing studies depend mainly on survey and sociodemographic data for disaster impacts and recovery effort evaluations, although such data has limitations, including large data collection efforts and delayed timeliness results. Also, there are very few studies have concentrated on spatial patterns of disaster impacts and short-term recovery of communities, although such investigation can enhance situational awareness during disasters and support the identification of disparate spatial patterns of disaster impacts and recovery in the impacted regions. This study examines CCTs data Harris County (Texas, USA) during Hurricane Harvey in 2017 to explore spatial patterns of disaster impacts and recovery duration from the perspective of community residents and businesses at ZIP-code and county scales, respectively, and to further investigate their spatial disparities across ZIP codes. The results indicate that individuals in ZIP codes with populations of higher income experienced more severe disaster impact and recovered more quickly than those located in lower income ZIP codes for most business sectors. Our findings not only enhance the understanding of spatial patterns and disparities in disaster impacts and recovery for better community resilience assessment but also could benefit emergency managers, city planners, and public officials in enhanced situational awareness and resource allocation.

Credit Card Fraud Detection

Abstract: Now a day’s online transactions have become an important and necessary part of our lives. 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. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Such problems can be tackled with Machine Learning with its algorithms. 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 analyzing and preprocessing 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. Keywords: Credit Card, Python, Detection

Design of a Model in Machine Learning For Credit Card Fraud Detection

In e-commerce, fraud has become a major problem, and much effort is being invested into identifying and preventing it. Currently, fraud detection and prevention systems are only able to detect and prevent a small percentage of fraudulent transactions, resulting in billions of dollars in losses. Because online transactions are likely to grow dramatically in the coming year, better fraud detection and prevention is critical. We provide a data-driven strategy for estimating the likelihood of a fraudulent or legal transaction based on machine learning techniques applied to large data sets. To predict the likelihood of a customer's next transaction being fraudulent, the algorithm was trained using past e-commerce credit card transaction data. Random Forest, Support Vector Machine, Gradient Boost, and combinations of these are used to compare the performance of supervised machine learning approaches. The problem of class imbalance is considered before the model is trained on a classifier, and methods such as oversampling and data pre-processing are employed. Keywords : machine learning, model, fraud, credit card DOI: 10.7176/CEIS/13-2-06 Publication date: April 30 th 2022

Integrating Machine Learning Algorithms With Quantum Annealing Solvers for Online Fraud Detection

Machine learning has been increasingly applied in identification of fraudulent transactions. However, most application systems can only detect the incidents after they have already occurred, not at or near real time. As spurious transactions are far fewer than the normal ones, the highly imbalanced data makes fraud detection even more challenging. This study has proposed a detection framework and implemented it using Support Vector Machine (SVM) enhanced with quantum annealing solvers. To evaluate its detection performance and examine the impact of feature selection, we have applied this quantum machine learning (QML) system along with systems built with twelve traditional machine learning methods on two datasets: Israel credit card transactions (non-time series) which is moderately imbalanced and a bank loan dataset (time series) that is highly imbalanced. The result shows that, the quantum enhanced SVM has categorically outperformed the rest in both speed and accuracy with the bank loan dataset. However, it’s detection accuracy is similar to others with Israel credit card transactions data. Furthermore, for both datasets, feature selection has been shown to significantly improve the detection speed, although the improvement on accuracy is marginal. These findings have demonstrated the potential of QML applications on time series based, highly imbalanced data, and the merit of traditional machine learning approaches in non-time series data. This study provides insight on selecting appropriate approach with different types of datasets while taking the tradeoffs of speed, accuracy, and cost into consideration.

Revisiting Jane Jacobs: Quantifying urban diversity

This study attempts to formally quantify Jane Jacob’s notion of urban diversity and examine whether greater diversity actually contributes economic benefits to a neighborhood. Focusing on the number and types of stores at the street level, we use the Shannon–Weaver index to quantify commercial diversity. We then compare the obtained degrees of diversity with store sales volumes obtained through credit card transaction data aggregated in the neighborhood divided into a 200-m grid. The results of the analysis, performed on 50 Spanish cities, show that the greater the diversity in the grid, the higher the sales volumes of the stores, and this tendency is more evident in large than in small–medium cities. In addition, we found that the coexistence of different store types provides a positive environment for the emergence of hub stores. We specifically define a hub store in this paper as the store with the largest revenue within a grid, provided that the distribution of the sales revenue in a grid is statistically similar to the power law. We speculate that hub stores trigger exploration between different store types, and consequently, the sales volumes of highly diverse neighborhoods increase compared with those of less diverse neighborhoods. These results highlight the importance of urban diversity for economic prosperity, which can lead to an increased quality of life for city neighborhoods.

Credit Card Fraud Detection with Autoencoder and Probabilistic Random Forest

This paper proposes a method, called autoencoder with probabilistic random forest (AE-PRF), for detecting credit card frauds. The proposed AE-PRF method first utilizes the autoencoder to extract features of low-dimensionality from credit card transaction data features of high-dimensionality. It then relies on the random forest, an ensemble learning mechanism using the bootstrap aggregating (bagging) concept, with probabilistic classification to classify data as fraudulent or normal. The credit card fraud detection (CCFD) dataset is applied to AE-PRF for performance evaluation and comparison. The CCFD dataset contains large numbers of credit card transactions of European cardholders; it is highly imbalanced since its normal transactions far outnumber fraudulent transactions. Data resampling schemes like the synthetic minority oversampling technique (SMOTE), adaptive synthetic (ADASYN), and Tomek link (T-Link) are applied to the CCFD dataset to balance the numbers of normal and fraudulent transactions for improving AE-PRF performance. Experimental results show that the performance of AE-PRF does not vary much whether resampling schemes are applied to the dataset or not. This indicates that AE-PRF is naturally suitable for dealing with imbalanced datasets. When compared with related methods, AE-PRF has relatively excellent performance in terms of accuracy, the true positive rate, the true negative rate, the Matthews correlation coefficient, and the area under the receiver operating characteristic curve.

City consumption profile: a city perspective on the spending behavior of citizens

In designing the city of the future, city managers and urban planners are driven by specific citizens’ behaviors. In fact, economic and financial behaviors, and specifically, which goods and services citizens purchase and how they allocate their spending, are playing a central role in planning targeted services. In this context, cashless payments provide an invaluable data source to identify such spending behaviors. In this work, we propose a methodology to extract the consumption behaviors of a large sample of customers through credit card transaction data. The main outcome of the methodology is a concise representation of the economic behavior of people residing in a city, the so-called city consumption profile. We inferred the city consumption profile from a network-based representation of the similarity among the customers in terms of purchase allocation; on top of which we applied a community detection algorithm to identify the representative consumption profiles. By applying the above methodology to a set of credit card transactions of an Italian financial group, we showed that cities, even geographically close, exhibit different profiles which makes them unique. Specifically, usage patterns focused on a single type of good/service—mono-categorical consumption profile—are the main factors leading to the differences in the city profiles. Our analysis also showed that there is a group of consumption profiles common to all cities, made up by purchases of primary goods/services, such as food or clothing. In general, the city consumption profile represents a tool for understanding the economic behaviors of the citizens and for comparing different cities. Moreover, city planners and managers may use it in the outline of city services tailored to the citizens’ needs.

Credit Card Fraud Detection using Machine Learning and Data Science

It is important that companies are able to identify fraudulent credit card transactions so that customers are not charged for items that they did not purchase. These problems can be handled with Data Science and its importance, along with Machine Learning. This project aim is to illustrate the modelling of a data set using machine learning with Credit Card. Our objective is to detect 100% of the fraudulent transactions while minimizing the incorrect fraud classifications. Credit Card Fraud Detection is a 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.

I Know What You Bought At Chipotle for $9.81 by Solving A Linear Inverse Problem

We consider the question of identifying which set of products are purchased and at what prices in a given transaction by observing only the total amount spent in the transaction, and nothing more. The ability to solve such an inverse problem can lead to refined information about consumer spending by simply observing anonymized credit card transactions data. Indeed, when considered in isolation, it is impossible to identify the products purchased and their prices from a given transaction based on just the transaction total. However, given a large number of transactions, there may be a hope. As the main contribution of this work, we provide a robust estimation algorithm for decomposing transaction totals into the underlying, individual product(s) purchased by utilizing a large corpus of transactions. Our method recovers a (product prices) vector $p ∈ RN>0 of unknown dimension (number of products) N as well as matrix $A ∈ ZM x N≥0 simply from M observations (transaction totals) y ∈ RM>0 such that y = A p + η with η ∈ RM representing noise (taxes, discounts, etc.). We formally establish that our algorithm identifies N, A precisely and p approximately, as long as each product is purchased individually at least once, i.e. M ≥ N and A has rank N. Computationally, the algorithm runs in polynomial time (with respect to problem parameters), and thus we provide a computationally efficient and statistically robust method for solving such inverse problems. We apply the algorithm to a large corpus of anonymized consumer credit card transactions in the period 2016-2019, with data obtained from a commercial data vendor. The transactions are associated with spending at Apple, Chipotle, Netflix, and Spotify. From just transactions data, our algorithm identifies (i) key price points (without access to the listed prices), (ii) products purchased within a transaction, (iii) product launches, and (iv) evidence of a new 'secret' product from Netflix - rumored to be in limited release.

A Heterogeneous Ensemble Learning Model Based on Data Distribution for Credit Card Fraud Detection

Credit card fraud detection (CCFD) is important for protecting the cardholder’s property and the reputation of banks. Class imbalance in credit card transaction data is a primary factor affecting the classification performance of current detection models. However, prior approaches are aimed at improving the prediction accuracy of the minority class samples (fraudulent transactions), but this usually leads to a significant drop in the model’s predictive performance for the majority class samples (legal transactions), which greatly increases the investigation cost for banks. In this paper, we propose a heterogeneous ensemble learning model based on data distribution (HELMDD) to deal with imbalanced data in CCFD. We validate the effectiveness of HELMDD on two real credit card datasets. The experimental results demonstrate that compared with current state‐of‐the‐art models, HELMDD has the best comprehensive performance. HELMDD not only achieves good recall rates for both the minority class and the majority class but also increases the savings rate for banks to 0.8623 and 0.6696, respectively.

Changes in Consumer Behaviour in the Post-COVID-19 Era in Seoul, South Korea

To prevent the spread of COVID-19, the Korean government promoted strong social distancing policies and restricted the use of confined areas and spaces that are likely to cause widespread infection, including religious facilities. The policies affect the consumption behaviours of Korean citizens. The purpose of this study is to examine changes in the consumer behaviours of citizens following the outbreak of COVID-19 in South Korea. Using credit card data from January to June 2020 in Seoul, this study examines the changes in consumption by industry type. Consumption types were classified into education, wholesale and retail, online purchases, food service, leisure, and travel. The industry that was most affected was the travel industry, which did not recover following the decline in consumption due to COVID-19. To examine consumer changes in credit card transactions due to widespread infection, a correlation analysis was conducted between the amount of consumption according to credit card transaction data (card consumption) and the number of confirmed patients and policy implementation by step. For more detailed analyses, group infections in the Guro-gu and Yongsan-gu neighbourhoods were investigated. In Guro-gu, no significant results were found in the area experiencing massive group infection. In Yongsan-gu, a significant negative correlation in consumption and number of cases was found in Itaewon 1-dong, an area with mass infection, and a positive correlation was found in the surrounding areas. Nevertheless, no significant correlations between changes in consumer behaviours and effects of COVID-19 were found as a result of the analysis herein.