Predicting Credit Card Transaction Fraud Using Machine Learning Algorithms

Gao, Jiaxin; Zhou, Zirui; Ai, Jiangshan; Xia, Bingxin; Coggeshall, Stephen

doi:10.4236/jilsa.2019.113003

Cited by 20 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The focus of this approach is to overcome the imbalanced data set issues by removing outlier observations from the majority class. In the paper [4], Logistic regression, artificial neural networks, support vector machines, random forest, and boosted trees have been introduced for fraud detection. The paper [5], proposes a hybrid model consisting of the following classifiers: J48, Meta Pagging, RandomTree, REPTree, AdaBoostM1, DecisionStump, and NaiveBayes to increase the recognition rate and improve the system performance.…”

Section: Related Workmentioning

confidence: 99%

Waste Management System Fraud Detection Using Machine Learning Algorithms to Minimize Penalties Avoidance and Redemption Abuse

et al. 2021

View full text Add to dashboard Cite

Online frauds have pernicious impacts on different system domains, including waste management systems. Fraudsters illegally obtain rewards for their recycling activities or avoid penalties for those who are required to recycle their own waste. Although some approaches have been introduced to prevent such fraudulent activities, the fraudsters continuously seek new ways to commit illegal actions. Machine learning technology has shown significant and impressive results in identifying new online fraud patterns in different system domains such as e-commerce, insurance, and banking. The purpose of this paper, therefore, is to analyze a waste management system and develop a machine learning model to detect fraud in the system. The intended system allows consumers, individuals, and organizations to track, monitor, and update their performance in their recycling activities. The data set provided by a waste management organization is used for the analysis and the model training. This data set contains transactions of users’ recycling activities and behaviors. Three machine learning algorithms, random forest, support vector machine, and multi-layer perceptron are used in the experiments and the best detection model is selected based on the model’s performance. Results show that each of these algorithms can be used for fraud detection in waste managements with high accuracy. The random forest algorithm produces the optimal model with an accuracy of 96.33%, F1-score of 95.20%, and ROC of 98.92%.

show abstract

Section: Related Workmentioning

confidence: 99%

Waste Management System Fraud Detection Using Machine Learning Algorithms to Minimize Penalties Avoidance and Redemption Abuse

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Therefore, non-contact video-based remote HR estimation methods have been investigated to mitigate these issues . Over the years, DeepNeural Networks have been used extensively to remotely obtain the heart rate from facial video [5][6][7][8][9][10][27][28][29][30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

Neural Network Interpretability for Facial rPPG Videos

Schmidt²,

Jain

et al. 2023

Preprint

View full text Add to dashboard Cite

Assessing lung function and treating chronic pulmonary diseases require the estimation and monitoring of remote heart rate (HR). With the COVID-19 pandemic, the importance of early detection of changes in remote HR has become more apparent, especially in asymptomatic patients with clinical deterioration. However, traditional remote HR measurement methods rely on contact-based sensing, which can lead to cross-contamination and complications in patients with impaired limb perfusion. Pulse oximeters, which are commonly used for remote HR measurement, may also be unavailable in marginalized communities and underdeveloped countries. The system includes three main steps: 1) extraction of the region of interest (ROI), which includes the palm and back of the hand, from the smartphone-captured videos; 2) spatial averaging of the ROI to produce R, G, and B time series; and 3) feeding the time series into an optophysiology-inspired CNN for remote HR estimation. This method is more efficient and accurate for monitoring remote HR using videos captured from consumer-grade smartphones, which is particularly useful in telehealth and health screening settings. It can provide a comfortable and unobtrusive way to monitor remote HR without the risk of cross-contamination and the limitations of conventional methods, such as the availability of pulse oximeters.

show abstract

“…There are also combinations of features that can be created per channel, per time interval, per currency. The complete list of 237 transactional candidate features (related to the similar field of credit card fraud ) has been shown in [3]. As a result, feature engineering (feature creation and selection) for AML is an essential yet very challenging and a time-consuming problem, as specified in [4]- [6].…”

Section: Introductionmentioning

confidence: 99%

A robust AI Agent-based approach to tackle and prevent Money Laundering

Wang¹,

Singh

Li³

2022

Preprint

View full text Add to dashboard Cite

The huge amount of bank operations that occur every day makes it extremely hard for financial institutions to spot malicious money laundering related operations. Although some predefined heuristics are used they aren't restrictive enough, still leaving to much work for human analyzers. This motivates the need for intelligent systems that can help financial institutions fight money laundering in a diversity of ways, such as: intelligent filtering of bank operations, intelligent analysis of suspicious operations, learning of new detection and analysis rules. In this paper, we present a multiagent based approach to deal with the problem of money laundering by defining a multiagent system designed to help financial institutions in this task, helping them to deal with two main problems: volume and rule improvement. We define the agent architecture, and characterize the different types of agents, considering the distinct roles they play in the process.

show abstract

Predicting Credit Card Transaction Fraud Using Machine Learning Algorithms

Cited by 20 publications

References 11 publications

Waste Management System Fraud Detection Using Machine Learning Algorithms to Minimize Penalties Avoidance and Redemption Abuse

Waste Management System Fraud Detection Using Machine Learning Algorithms to Minimize Penalties Avoidance and Redemption Abuse

Neural Network Interpretability for Facial rPPG Videos

A robust AI Agent-based approach to tackle and prevent Money Laundering

Contact Info

Product

Resources

About