摘要
针对全球情况严重的信用卡欺诈问题,综合了国内外的信用卡欺诈问题研究现状和方法,分析了这些方法的优缺点,提出将随机森林的方法运用到信用卡欺诈检测问题上,然后与传统的研究方法做出对比,本文的研究重点从数据本身出发,给出数据挖掘流程,深究其数据背后隐藏的信息,挖掘其相关欺诈信息,选择合适分类算法,调节好参数,发现随机森林的方法在信用卡欺诈检测问题上的精确率和召回率都有比较好的结果。
This paper analyzes the current situation and methods of credit card fraud at home and abroad for the problem of credit card fraud in the global situation.It also analyzes the advantages and disadvantages of these methods and proposes to apply the random forest method to the detection of credit card fraud.This methos will be compared with the traditional research methods.The research focus on the data itself and gives the process of data mining to deep the hidden information behind the data and mine its related fraud information.As the same time,selecting the appropriate classification algorithm and adjusting its parameters are also important thing.Finally,we find the method of random forests has a better result on the accuracy and recall rate of the detection of credit card fraud.
作者
李梦涛
吕朝辉
LI Meng-tao;LV Zhao-hui(School of Information Engineering,Communication University of China,Beijing 100024,China)
出处
《中国传媒大学学报（自然科学版）》
2020年第6期69-73,共5页
Journal of Communication University of China：Science and Technology
关键词
信用卡
欺诈
数据挖掘
检测
credit card
fraud
data mining
detection
作者简介
李梦涛(1994-),男(汉族),安徽蚌埠人,中国传媒大学硕士研究生.E-mail:1449047566@qq.com
