The effect of feature extraction and data sampling on credit card fraud detection

Salekshahrezaee, Zahra; Leevy, Joffrey L.; Khoshgoftaar, Taghi M.

doi:10.1186/s40537-023-00684-w

Cited by 36 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, Salekshahrezaee et al [43] aimed to develop robust CCFD models by studying the impact of feature extraction and data resampling on the following machine learning classifiers: CatBoost, random forest, extreme gradient boosting (XGBoost), and LightGBM. The feature extraction was achieved using principal component analysis (PCA) and convolutional autoencoder (CAE), while the data resampling methods include SMOTE, random undersampling (RUS), and SMOTE Tomek techniques.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

Mienye

Sun

2023

IEEE Access

View full text Add to dashboard Cite

Credit cards play an essential role in today's digital economy, and their usage has recently grown tremendously, accompanied by a corresponding increase in credit card fraud. Machine learning (ML) algorithms have been utilized for credit card fraud detection. However, the dynamic shopping patterns of credit card holders and the class imbalance problem have made it difficult for ML classifiers to achieve optimal performance. In order to solve this problem, this paper proposes a robust deep-learning approach that consists of long short-term memory (LSTM) and gated recurrent unit (GRU) neural networks as base learners in a stacking ensemble framework, with a multilayer perceptron (MLP) as the meta-learner. Meanwhile, the hybrid synthetic minority oversampling technique and edited nearest neighbor (SMOTE-ENN) method is employed to balance the class distribution in the dataset. The experimental results showed that combining the proposed deep learning ensemble with the SMOTE-ENN method achieved a sensitivity and specificity of 1.000 and 0.997, respectively, which is superior to other widely used ML classifiers and methods in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

Mienye

Sun

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To detect credit card fraud, Salekshahrezaee et al [15] utilized four integrated learning classifiers based on Decision Tree (DT) classifiers in conjunction with distinct feature selection approaches. Also, their dataset was produced by the Kaggle community.…”

Section: Related Workmentioning

confidence: 99%

Assessing the feasibility of machine learning-based modelling and prediction of credit fraud outcomes using hyperparameter tuning

2023

ACSS

View full text Add to dashboard Cite

Both the actual theft of a credit card and the deletion of private credit card data are considered forms of credit card fraud. For detection, there are numerous machine learning algorithms accessible. So, several algorithms that can be used to categorize transactions as fraudulent or lawful are illustrated in this study. In this experiment, the credit card fraud prediction dataset was utilized. The dataset is extremely skewed, hence undersampling is used rather than oversampling. The dataset is separated into test and training data portions, and feature selection is made. The experiment uses the methods of Logistic Regression, Random Forest, SVM, ADABoost, XGBoost, and LightGBM. Moreover, the SMOTE and Optuna's hyperparameter tweaking ways provide model customization. The findings suggest that specific algorithms may be capable of accurately recognizing credit card fraud.

show abstract

“…See the references [20][21][22] for data, R code and an analytic method of COVID data respectively. The harmonic mean is used to portray the uncertainty panarthropod relationship [23] in multicriteria optimization [24], in feature extraction of credit card frauds [25], in Bayesian analysis of atherosclerosis cardiovascular data analysis [26], and in hierarchical taxonomy [27], among many other scientific applications. In other words, the number of zero counts is equal to n − n Biased , where n is the number of entries in the original data.…”

Section: Incidence-rate-restricted Poisson Model With a Complementary...mentioning

confidence: 99%

Indexing of US Counties with Overdispersed Incidences of COVID-19 Deaths

et al. 2023

View full text Add to dashboard Cite

The number of COVID-19 fatalities fluctuated widely across United States (US) counties. The number of deaths is stochastic. When the average number of deaths is equal to the dispersion, the distribution is the usual Poisson. When the average number of deaths is higher than the dispersion, the distribution is an intervened Poisson. When the average number of deaths is lower than the dispersion, the distribution is an incidence-rate-restricted Poisson (IRRP) type. Because dispersion of COVID-19 fatalities in some counties is higher than the average number of fatalities, the underlying model for the chance-oriented mechanism might be IRRP. Understanding where this overdispersion or volatility exists and the implications of it is the topic of this research. In essence, this paper focuses on the number of COVID-19 fatalities that fluctuated widely across United States (US) counties and develops an incidence-rate-restricted Poisson (IRRP) to understand where this overdispersion or volatility exists and the implications of it.

show abstract

The effect of feature extraction and data sampling on credit card fraud detection

Cited by 36 publications

References 45 publications

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

A Deep Learning Ensemble With Data Resampling for Credit Card Fraud Detection

Assessing the feasibility of machine learning-based modelling and prediction of credit fraud outcomes using hyperparameter tuning

Indexing of US Counties with Overdispersed Incidences of COVID-19 Deaths

Contact Info

Product

Resources

About