Using neural network for credit card fraud detection

Georgieva, Sevdalina; Markova, Maya; Pavlov, Velizar

doi:10.1063/1.5127478

Cited by 26 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach positively affects the model's performance. In [10], a neural network is used to establish a fraud detection system on 900 samples of labeled credit card account transactions. The initial data set was imbalanced, where the genuine labels were more than fraudulent.…”

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

“…Feedforward Neural Network is a type of neural network were data flows in one direction [17]. It is a supervised learning model.…”

Section: Feedforward Neural Networkmentioning

confidence: 99%

Service-Based Credit Card Fraud Detection Using Oracle SOA Suite

et al. 2021

View full text Add to dashboard Cite

Credit card fraud detection techniques help to capture fraudulent transactions carried out by illegitimate users and thus prevent any misuse of the credit card. Due to the technological advancement, credit card usage has been on the rise of financial transactions keeping aside the risk of increase in number of fraudulent transactions. Thus, some sort of improved strategies are desired to be implemented to curb and avoid such fraudulent transactions. This study intends to propose a fraud detection technique by implementing various machine learning techniques on cloud platform which itself is based on service-oriented architecture (SOA). SOA helps to create applications by making use of services available over the network. Furthermore, this credit card fraud detection technique, focuses on orchestration of various services using Oracle SOA suite mingled with different machine learning models, such as support vector machine (SVM), isolation forest, random forest regressor, local outlier factor (LOF), and different neural networks, such as multilayer perceptron (MLP), autoencoder, and convolutional neural network (CNN). The outputs of all the machine learning models are integrated with Oracle SOA suite to provide proper agility and efficiency. In addition, this Oracle SOA suite model has been deployed on Google cloud platform (GCP) for providing reliable solution in an online mode. A comparative analysis on performance of different machine learning algorithms has been presented for their critical assessment.

show abstract

“…Article [10] suggested that a graph-based semi-supervised system should be used to solve the problem. This gradually expands the methodology for building fraud-detection systems; it should be noted that recently there has been more and more research on the use of resource-intensive technologies such as deep learning and artificial neural networks [11,12]. The main issue with these methods is the poor interpretability of the models obtained as a result of their application whereas it is the identification of fraud factors that contributes to the effective control of it.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

“…Papers [3,4,7,12,[16][17][18] focused on the use of such processes and methods of the input data analysis, which are fully under the control of the researcher. This is useful for investigating global patterns in data, but, in practical implementation, there are drawbacks such as high requirements for the researcher's qualifications, as well as a lot of time spent developing the analytical system and its subsequent maintenance.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Automatic machine learning algorithms for fraud detection in digital payment systems

Kolodiziev

Mints

Sidelov

et al. 2020

EEJET

View full text Add to dashboard Cite

Data on global financial statistics demonstrate that total losses from fraudulent transactions around the world are constantly growing. The issue of payment fraud will be exacerbated by the digitalization of economic relations, in particular the introduction by banks of the concept of "Bank-as-a-Service", which will increase the burden on payment services. The aim of this study is to synthesize effective models for detecting fraud in digital payment systems using automated machine learning and Big Data analysis algorithms. Approaches to expanding the information base to detect fraudulent transactions have been proposed and systematized. The choice of performance metrics for building and comparing models has been substantiated. The use of automatic machine learning algorithms has been proposed to resolve the issue, which makes it possible in a short time to go through a large number of variants of models, their ensembles, and input data sets. As a result, our experiments allowed us to obtain the quality of classification based on the AUC metric at the level of 0.977-0.982. This exceeds the effectiveness of the classifiers developed by traditional methods, even as the time spent on the synthesis of the models is much less and measured in hours. The models' ensemble has made it possible to detect up to 85.7 % of fraudulent transactions in the sample. The accuracy of fraud detection is also high (79-85 %). The results of our study confirm the effectiveness of using automatic machine learning algorithms to synthesize fraud detection models in digital payment systems. In this case, efficiency is manifested not only by the resulting classifiers' quality but also by the reduction in the cost of their development, as well as by the high potential of interpretability. Implementing the study results could enable financial institutions to reduce the financial and temporal costs of developing and updating active systems against payment fraud, as well as improve the effectiveness of monitoring financial transactions

show abstract

Using neural network for credit card fraud detection

Cited by 26 publications

References 7 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

Service-Based Credit Card Fraud Detection Using Oracle SOA Suite

Automatic machine learning algorithms for fraud detection in digital payment systems

Contact Info

Product

Resources

About