2021
DOI: 10.1007/978-981-16-2275-5_16
|View full text |Cite
|
Sign up to set email alerts
|

A Comparative Analysis of Credit Card Fraud Detection Using Machine Learning and Deep Learning Techniques

Abstract: E-commerce is growing rapidly around the world and this causes a significant increase in credit card transactions, both normal and fraud transactions. Financial institutions throughout the world lose billions because of credit card fraud. Fraudsters have no fixed styles; they always change their behavior and try to learn new technologies that allow them to commit frauds through online transactions. Moreover, they assume that the regular behavior of consumers and fraud patterns change fast. Fraud detection syst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 9 publications
0
4
0
Order By: Relevance
“…The end goal of the prediction must be evident in the first place, and that must be defined in this phase. For instance, a prediction could be straightforward 'yes or no' only, such as predicting if a credit card is a fraud or not [14]. It could also forecast more than two classifications, such as [15] recognizing chronic kidney diseases or early detection of possible heart disease [16].…”
Section: Related Work a Understanding Predictive Analytics Process An...mentioning
confidence: 99%
See 2 more Smart Citations
“…The end goal of the prediction must be evident in the first place, and that must be defined in this phase. For instance, a prediction could be straightforward 'yes or no' only, such as predicting if a credit card is a fraud or not [14]. It could also forecast more than two classifications, such as [15] recognizing chronic kidney diseases or early detection of possible heart disease [16].…”
Section: Related Work a Understanding Predictive Analytics Process An...mentioning
confidence: 99%
“…The pronouncement of both studies with different algorithms as the best-performing algorithm is essential to this study since it also deals with prediction using student data; this shows, however, that results also depend on the preprocessing procedure, the data itself, and the algorithm. It also must be noted that studies included in the Table II deal with either binary problem classification [14] or school-related problems, such as the possibility of a student dropping out [45].…”
Section: F Researches In Predictive Analytics Domainmentioning
confidence: 99%
See 1 more Smart Citation
“…The performance of machine learning methods varied across individual business cases, with factors such as the number of features, transactions, and feature correlations influencing the model's effectiveness [153]. For example, in a comparative analysis of Credit Card Fraud Detection, a random forest model showed slightly better accuracy than a deep neural network [154]. However, in another study on credit card fraud detection, BiLSTM and BiGRU out-performed naïve Bayes, Adaboost, random forest, decision tree, and logistic regression [155].…”
Section: Fraud Detectionmentioning
confidence: 99%