Novel Machine Learning Approach for Analyzing Anonymous Credit Card Fraud Patterns

Q3 Computer Science

International Journal of Electronic Commerce Studies Pub Date : 2019-12-01 DOI:10.7903/ijecs.1732

Sylvester Manlangit, S. Azam, Bharanidharan Shanmugam, Asif Karim

{"title":"Novel Machine Learning Approach for Analyzing Anonymous Credit Card Fraud Patterns","authors":"Sylvester Manlangit, S. Azam, Bharanidharan Shanmugam, Asif Karim","doi":"10.7903/ijecs.1732","DOIUrl":null,"url":null,"abstract":"Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32% and 97.44% respectively for k-NN and 100% and 98.24% respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown. To cite this document: Sylvester Manlangit, Sami Azam, Bharanidharan Shanmugam, and Asif karim, \"Novel Machine Learning Approach for Analyzing Anonymous Credit Card Fraud Patterns\", International Journal of Electronic Commerce Studies, Vol.10, No.2, pp.175-202, 2019. Permanent link to this document: http://dx.doi.org/10.7903/ijecs.1732","PeriodicalId":38305,"journal":{"name":"International Journal of Electronic Commerce Studies","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Electronic Commerce Studies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7903/ijecs.1732","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 11

Abstract

Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32% and 97.44% respectively for k-NN and 100% and 98.24% respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown. To cite this document: Sylvester Manlangit, Sami Azam, Bharanidharan Shanmugam, and Asif karim, "Novel Machine Learning Approach for Analyzing Anonymous Credit Card Fraud Patterns", International Journal of Electronic Commerce Studies, Vol.10, No.2, pp.175-202, 2019. Permanent link to this document: http://dx.doi.org/10.7903/ijecs.1732

查看原文本刊更多论文

分析匿名信用卡欺诈模式的新机器学习方法

欺诈性信用卡交易呈上升趋势，已成为金融直觉和个人面临的一个重大问题。已经采取了各种方法来处理这个问题，但贪污者总是设法采用创新的策略来规避一些安全措施并进行欺诈交易。因此，解决这种复杂的数字盗窃问题的答案应该是一种基于智能和适应性的机器学习算法，而不是基于规则的系统。所提出的框架使用k-NN进行分类，并使用主成分分析（PCA）进行原始数据转换。使用合成少数过采样技术（SMOTE）创建邻居（数据中的异常），并采用基于距离的特征选择方法。当使用错误分类的实例时，所提出的过程表现良好，k-NN的精度和F-Score分别为98.32%和97.44%，Time子集的精度和F-评分分别为100%和98.24%。这项工作还展示了一个更大、更清晰的分类分解，有助于实现更高的准确率和更高的召回率。为了实现如此高的精度，使用主成分分析（PCA）转换原始数据，使用合成少数过采样技术（SMOTE）创建邻居（数据中的异常），并采用基于距离的特征选择方法。当使用先前工作中使用的测试数据集中的错误分类实例时，所提出的过程表现良好，同时展示了更大、更清晰的分类分解。引用本文件：Sylvester Manlangit、Sami Azam、Bharanidharan Shanmugam和Asif karim，“分析匿名信用卡欺诈模式的新型机器学习方法”，《国际电子商务研究杂志》，第10卷，第2期，第175-2022019页。本文件的永久链接：http://dx.doi.org/10.7903/ijecs.1732

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Electronic Commerce Studies Computer Science-Computer Science Applications

CiteScore

1.40

自引率

0.00%

发文量

期刊介绍： The IJECS is a double-blind referred academic journal for all fields of Electronic Commerce. To serve as an international platform, the IJECS encourages manuscript submissions from authors all around the world. As a multi-discipline journal, The IJECS welcome both technology oriented and business oriented electronic commerce research articles. The purpose of the International Journal of Electronic Commerce Studies is to promote electronic commerce research and provide worldwide scholars a place to publish their innovative work in electronic commerce. To be published in the journal, the manuscript must make strong empirical, theoretical, or practical contributions and highlight the significance of the contributions to the electronic commerce field. Thus, preference is given to submissions that test, extend, or build strong theoretical frameworks for electronic commerce theory, electronic commerce system development, and electronic commerce practice. The journal is not tied to any particular national context; the geographic distribution of authors publishing in the journal came from countries around the world. Articles introducing cases of innovative applications in electronic commerce around the world are also published in the journal. The journal provides scholars opportunities to realize the electronic commerce research and development around the world. Articles in the International Journal of Electronic Commerce Studies will include, but are not limited to the following areas.