Survey on Credit Card Fraud Detection Techniques

Shimpi, Priya Ravindra; Kadroli, Vijayalaxmi

doi:10.18535/ijecs/v4i11.25

Cited by 6 publications

(3 citation statements)

References 3 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification based: these supervised techniques make the assumption that a classifier of anomalies can be learnt from a training set and that the test set distribution is not significantly different from the training one. Several supervised machine learning algorithms have been discussed in literature [40,43,53]. In most cases an optimal detection can be obtained by combining multiple supervised machine learning techniques.…”

Section: Passive Learning For Fraud Detectionmentioning

confidence: 99%

Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization

Carcillo

Borgne

Caelen

et al. 2018

Int J Data Sci Anal

View full text Add to dashboard Cite

Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data is peculiar because they are obtained in a streaming fashion, they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated to the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature. 1

show abstract

Section: Passive Learning For Fraud Detectionmentioning

confidence: 99%

Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization

Carcillo

Borgne

Caelen

et al. 2018

Int J Data Sci Anal

View full text Add to dashboard Cite

show abstract

“…The Random Forest Algorithm appears to produce the most variable results with its standard deviation ranging from the lower 87's to the upper 95'. (Shimpi et al 2016)Limitations using the credit card data set are most sensitive and noisy. The outliers like (PCA), (LOC) using parameters are very sensitive in the dataset.…”

Section: Resultsmentioning

confidence: 99%

An Innovative Method to Enhance the Accuracy of Credit Card Fraud Detection Using Logistic Regression Algorithm by Comparing Random Forest Algorithm

Poojitha¹,

Malathi²

2022

ECS Trans.

View full text Add to dashboard Cite

Aim: The objective is to develop a model to predict which transactions could be fraud with a high accuracy rate by using machine learning(ML) methods, such as the innovative Random Forest Algorithm. Materials and Methods: F1 score and accuracy rate are performed on fraud rates transactions in a dataset. The two groups (LR) the sample size is (N=20) and (RF) is (N=20) with G power value = 80. Results: To perform the transactions in the credit card by utilizing the card number, financial balance and client details, and if it is offline, the fraud has to steal the user's details in online transactions, which is not easily recognized by the client and bank authority, which prompts loss of sensitive data. (p<0.05) statistically significant value is compared to the amount and time since last purchase with a confidence level of 95% (=.519). (RF) algorithm is used for detecting credit card fraud. The accuracy is analyzed based on the dataset of 99.3%, where the (LR) has the accuracy of 99.1%. Conclusion: The performance of strategy is measured based on accuracy, F1 score, Precision, Recall. The results seem to be better accuracy for (RF) is 93.3%.

show abstract

“…Despite the existing efforts aimed at developing efficient data-driven approaches for fraud detection, such as modelbased reasoning or descriptive data mining techniques, a reliable model with better practicality is still a requirement. Fraud detection methods and techniques are considered as intellectual assets of banks and other financial institutions [8]. Data-driven methods are bound to various requirements and preserving the user privacy and not disclosing the same is pivotal while analysing relevant information.…”

Section: Introductionmentioning

confidence: 99%

Efficient Resampling for Fraud Detection During Anonymised Credit Card Transactions with Unbalanced Datasets

Mrozek

Panneerselvam

Bagdasar

2020

2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC)

View full text Add to dashboard Cite

The rapid growth of e-commerce and online shopping have resulted in an unprecedented increase in the amount of money that is annually lost to credit card fraudsters. In an attempt to address credit card fraud, researchers are leveraging the application of various machine learning techniques for efficiently detecting and preventing fraudulent credit card transactions. One of the prevalent common issues around the analytics of credit card transactions is the highly unbalanced nature of the datasets, which is frequently associated with the binary classification problems. This paper intends to review, analyse and implement a selection of notable machine learning algorithms such as Logistic Regression, Random Forest, K-Nearest Neighbours and Stochastic Gradient Descent, with the motivation of empirically evaluating their efficiencies in handling unbalanced datasets whilst detecting credit card fraud transactions. A publicly available dataset comprising 284807 transactions of European cardholders is analysed and trained with the studied machine learning techniques to detect fraudulent transactions. Furthermore, this paper also evaluates the incorporation of two notable resampling methods, namely Random Under-sampling and Synthetic Majority Oversampling Techniques (SMOTE) in the aforementioned algorithms, in order to analyse their efficiency in handling unbalanced datasets. The proposed resampling methods significantly increased the detection ability, the most successful technique of combination of Random Forest with Random Under-sampling achieved the recall score of 100% in contrast to the recall score 77% of model without resampling technique. The key contribution of this paper is the postulation of efficient machine learning algorithms together with suitable resampling methods, suitable for credit card fraud detection with unbalanced dataset.

show abstract

Survey on Credit Card Fraud Detection Techniques

Cited by 6 publications

References 3 publications

Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization

Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization

An Innovative Method to Enhance the Accuracy of Credit Card Fraud Detection Using Logistic Regression Algorithm by Comparing Random Forest Algorithm

Efficient Resampling for Fraud Detection During Anonymised Credit Card Transactions with Unbalanced Datasets

Contact Info

Product

Resources

About