Credit Card Fraud Detection Using Improved Deep Learning Models
作者机构：Computer Science DepartmentAl-Mustansiriya UniversityBaghdad10001Iraq Computer Science DepartmentUniversity of BaghdadBaghdad10001Iraq Faculty of Basic EducationAl-Mustansiriya UniversityBaghdad10001Iraq
出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)
年 卷 期：2024年第78卷第1期
页 面：1049-1069页
核心收录：
学科分类：0839[工学-网络空间安全] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：Card fraud detection hyperparameter tuning deep learning autoencoder convolution neural network long short-term memory resampling
摘 要：Fraud of credit cards is a major issue for financial organizations and *** fraudulent actions become more complex,a demand for better fraud detection systems is *** learning approaches have shown promise in several fields,including detecting credit card ***,the efficacy of these models is heavily dependent on the careful selection of appropriate *** paper introduces models that integrate deep learning models with hyperparameter tuning techniques to learn the patterns and relationships within credit card transaction data,thereby improving fraud *** deep learning models:AutoEncoder(AE),Convolution Neural Network(CNN),and Long Short-Term Memory(LSTM)are proposed to investigate how hyperparameter adjustment impacts the efficacy of deep learning models used to identify credit card *** experiments conducted on a European credit card fraud dataset using different hyperparameters and three deep learning models demonstrate that the proposed models achieve a tradeoff between detection rate and precision,leading these models to be effective in accurately predicting credit card *** results demonstrate that LSTM significantly outperformed AE and CNN in terms of accuracy(99.2%),detection rate(93.3%),and area under the curve(96.3%).These proposed models have surpassed those of existing studies and are expected to make a significant contribution to the field of credit card fraud detection.
维普期刊数据库