Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/3569
Title: A design methodology for web-based services to detect fraudulent transactions in credit card
Authors: Prusti, Debachudamani
Kumar, Abhishek
Ingole, Shubham Purusottam
Rath, Santanu Kumar
Keywords: Machine learning
Ensemble methods,
Simple object access protocol(SOAP)
RESTful web service
Issue Date: Feb-2020
Citation: 14th Innovations in Software Engineering Conference (ISEC 2021), 25th- 27th February 2021, KIIT Bhubaneswar, INDIA
Abstract: Financial fraud associated with the transactions of credit card leads to unauthorized access of performing credit card transactions indifferent platforms by intercepting important card credentials. In order to curb this problem, an effective fraud detection system is of primary importance for any financial institution. In the pro-posed methodology, a web-based fraud detection system has been designed considering two different protocols for the web-based services such as simple object access protocol (SOAP) and representational state transfer (REST). Further, for detecting the fraudulent transactions, these services are associated with five different ma-chine learning techniques such as support vector machine (SVM),multilayer perceptron (MLP), random forest regression, auto en-coder and isolation forest. The performance analysis of each ma-chine learning algorithm associated with SOAP and REST services are critically assessed. The web services have been designed based on concepts of service oriented architecture (SOA) by considering a middle ware family of software products i.e., Oracle SOA suite which is very often used by the software architects.
Description: Copyright of this paper is with proceedings publisher
URI: http://hdl.handle.net/2080/3569
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
DPrusti_isec2021.pdf774.69 kBAdobe PDFView/Open    Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.