Analysis and Comparison of Credit Card Fraud Detection Using Machine Learning

Content Provider	Scilit
Author	Saloni Rout, Minakhi
Copyright Year	2021
Description	As per Reserve Bank of India (RBI) the number of credit card users is increasing rapidly. Due to the popularity of online banking, there is demand for more fraud detection techniques to protect or prevent cardholders from losses. The proposed method has been implemented on three publicly available data sets. To determine the fraud transaction various deep learning architecture like Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Convolutional Neural Network (CNN), and Multilayer Perceptron (MLP) have been used. Various parameters of deep learning like activation function, number of hidden layers, etc. have been used and it has tune to examine the performance of the model. All the collected data sets were imbalanced therefore, synthetic minority over-sampling technique (SMOTE) has been used. For the evaluation of the model F1 score has been considered as the main evaluation metrics. After the implementation it was discover that in all the three data sets the highest F1 score is achieved by the GRU architecture using sigmoid activation function, and two hidden layers when it compares with the other architecture. Book Name: Artificial Intelligence and Machine Learning in Business Management
Related Links	https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/9781003125129-5&type=chapterpdf
Ending Page	93
Page Count	13
Starting Page	81
DOI	10.1201/9781003125129-5
Language	English
Publisher	Informa UK Limited
Publisher Date	2021-09-16
Access Restriction	Open
Subject Keyword	Book Name: Artificial Intelligence and Machine Learning in Business Management Function Neural Credit Architecture
Content Type	Text
Resource Type	Chapter