지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 金輝剛
- 발행연도
- 2017
- 저작권
- 고려대학교 논문은 저작권에 의해 보호받습니다.
이용수4
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
전 세계적으로 스마트폰 보급률이 증가함에 따라 스마트폰을 이용한 다양한 결제 서비스들이 출시되었고, 모바일 결제로 금전을 탈취하는 사례도 증가하였다. 이미 금융권은 온/오프라인 환경에서 이상거래를 탐지하기 위한 다양한 보안 조치들을 마련하였지만, 모바일 결제 환경의 보안 솔루션이나 연구들은 미비한 실정이다. 모바일 결제는 소액 결제 위주의 결제 패턴을 보이고 결제 환경도 다르기 때문에 기존의 이상거래 탐지와는 다른 모바일에 특화된 이상거래 탐지가 필요하다. 이에 본 논문에서는 국내 PG사의 실제 모바일 결제 로그를 분석하고 데이터 마이닝 알고리즘을 이용한 모바일 결제에 특화된 이상거래 탐지 시스템을 제안하였다. 해당 시스템은 1단계 탐지 모듈에서 2가지 알고리즘을 사용해 빠른 속도로 정상거래를 판별하고, 2단계 탐지 모듈에서는 고도화된 3가지 알고리즘으로 이상거래를 정확히 탐지하도록 설계하였다. 그 결과 1초에 13건 이상의 거래를 93% 이상의 정확도로 판별할 수 있었다.
목차
1. 서론 ··································································12. 관련 연구 ·····························································41. 모바일 이상거래 탐지 ···············································42. 금융 이상거래 탐지 ·················································53. 이상거래 탐지 시스템 ··················································81. 데이터 소개 및 전처리 ··············································82. 피쳐 선택 ·························································123. 시스템 구조 ·······················································184. 알고리즘 ··························································201) 1단계 ·························································20(1) Decision tree(C4.5) ········································20(2) Naive bayes ···············································202) 2단계 ·························································21(1) CART(Classification And Regression Trees) ·················21(2) SMO(Sequential Minimal Optimization) ······················21(3) Random forest ·············································214. 실험 ·································································235. 결론 ·································································26부 록 ···································································27참 고 문 헌 ·····························································30
최근 본 자료
댓글(0)
0