Smart Acquiring Platform in Contactless Payments using Advanced Machine Learning : Security Controls using Device Recognition, Geo Fencing and Customer on File

Bharathan Kasthuri Rengan
{"title":"Smart Acquiring Platform in Contactless Payments using Advanced Machine Learning : Security Controls using Device Recognition, Geo Fencing and Customer on File","authors":"Bharathan Kasthuri Rengan","doi":"10.1109/LISAT58403.2023.10179552","DOIUrl":null,"url":null,"abstract":"Acquiring platform (Merchant Bank) today faces greater Merchant Fraud cases (catering to small medium business) post pandemic as new methods of payments are evolving. In many cases, the fraud merchants, present the legitimate Know Your Customer (KYC) documents and complete onboarding like a legitimate merchant profile. Acquirers need to mitigate the merchant risk in Payments (multiple method of payments – card Present, card Not Present, contactless Payments (Tap to Pay, Apple Pay, Samsung Pay, using Near-Field Communication (NFC) and biometric based payments), in Point of Sale (PoS) and in large ecommerce portals). To address this, acquiring platform needs to build a comprehensive risk management platform with large set of data from multiple sources (device activity, merchant activity over time, analyze merchant portfolio for a specific geography and finally line of business). Acquirer needs to also analyze KYC data as well as payment data (over period of time). While doing so, risk platform needs to address both account fraud and payments fraud. It also needs to balance accuracy in fraud detection and without compromising high authorization rates. As new payment methods emerge, it is critical that risk management platform gets data from various sources in addition to just KYC and payment data. These are device /peripherals – Internet of Things (IoT) data, leveraging estate management, tracking geo location, analyzing transaction pattern (over period of twenty hours), profiling merchants and merchant segmentation. Risk management platform needs to address PoS3 needs specifically.","PeriodicalId":250536,"journal":{"name":"2023 IEEE Long Island Systems, Applications and Technology Conference (LISAT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE Long Island Systems, Applications and Technology Conference (LISAT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LISAT58403.2023.10179552","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Acquiring platform (Merchant Bank) today faces greater Merchant Fraud cases (catering to small medium business) post pandemic as new methods of payments are evolving. In many cases, the fraud merchants, present the legitimate Know Your Customer (KYC) documents and complete onboarding like a legitimate merchant profile. Acquirers need to mitigate the merchant risk in Payments (multiple method of payments – card Present, card Not Present, contactless Payments (Tap to Pay, Apple Pay, Samsung Pay, using Near-Field Communication (NFC) and biometric based payments), in Point of Sale (PoS) and in large ecommerce portals). To address this, acquiring platform needs to build a comprehensive risk management platform with large set of data from multiple sources (device activity, merchant activity over time, analyze merchant portfolio for a specific geography and finally line of business). Acquirer needs to also analyze KYC data as well as payment data (over period of time). While doing so, risk platform needs to address both account fraud and payments fraud. It also needs to balance accuracy in fraud detection and without compromising high authorization rates. As new payment methods emerge, it is critical that risk management platform gets data from various sources in addition to just KYC and payment data. These are device /peripherals – Internet of Things (IoT) data, leveraging estate management, tracking geo location, analyzing transaction pattern (over period of twenty hours), profiling merchants and merchant segmentation. Risk management platform needs to address PoS3 needs specifically.
使用先进机器学习的非接触式支付智能收单平台:使用设备识别、地理围栏和客户档案的安全控制
随着新的支付方式不断发展,获取平台(商户银行)今天面临着更多的商家欺诈案件(迎合中小型企业)。在许多情况下,欺诈商家会提供合法的KYC (Know Your Customer)文件,并像合法的商家档案一样完成登录。收单方需要降低商家在支付(多种支付方式——有卡支付、无卡支付、非接触式支付(点击支付、苹果支付、三星支付、使用近场通信(NFC)和基于生物识别的支付)、销售点(PoS)和大型电子商务门户)方面的风险。为了解决这个问题,收购平台需要建立一个综合的风险管理平台,其中包含来自多个来源的大量数据(设备活动,商家活动随时间的变化,分析特定地理位置的商家组合,最后是业务线)。收单方还需要分析KYC数据以及支付数据(一段时间内)。在此过程中,风险平台需要同时解决账户欺诈和支付欺诈。它还需要在欺诈检测的准确性和不影响高授权率之间取得平衡。随着新的支付方式的出现,除了KYC和支付数据之外,风险管理平台从各种来源获取数据至关重要。这些是设备/外围设备-物联网(IoT)数据,利用物业管理,跟踪地理位置,分析交易模式(超过20小时),分析商家和商家细分。风险管理平台需要专门解决PoS3的需求。
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信