摘要
针对信用卡欺诈检测数据集存在不平衡、特征空间维度较高等问题,提出一种基于混合采样和自编码器结合的信用卡欺诈检测方法.用混合采样对数据集平衡化处理;应用自编码器对训练数据集进行降维,使用随机森林作为分类器检测欺诈行为,在ULB信用卡数据集上进行验证并与其他方法对比.结果表明本方法在信用卡欺诈检测方面表现良好.
In order to solve the problem of unbalanced data set and high dimension of feature space in credit card fraud detection,a credit card fraud detection method based on hybrid sampling and self-encoder was proposed.Mixed sampling was used to balance the data set.An autoencoder was used to reduce the dimension of the training data set.A random forest was used as a classifier to detect fraud.The ULB credit card data set was validated and compared with other methods.The results showed that the proposed method performs well in credit card fraud detection.
作者
赵峰
李妞妞
ZHAO Feng;LI Niu-niu(School of Management Science&Engineering,Anhui University of Technology,Maanshan 243032,China)
出处
《哈尔滨商业大学学报（自然科学版）》
CAS
2022年第4期420-426,共7页
Journal of Harbin University of Commerce：Natural Sciences Edition
基金
国家自然科学基金项目(71872002)
安徽省高校人文社会科学研究重点项目(SK2019A0072)。
关键词
欺诈检测
混合采样
自编码器
分类器集成
随机森林
card fraud detection
mixed sampling
autoencoder
classifier integration
random forests
