• Tamboli Sonali D
• Kadam Vishaka S
• Shinde Nikita N
• Tekale Pratiksha S
• Prof Vibha Lahane

With the popularization of on-line looking, dealings fraud is growing seriously. Therefore, the study on fraud detection is attention-grabbing and important. a vital manner of detective work fraud is to extract the behavior profiles (BPs) of users supported their historical dealings records, so to verify if AN incoming dealings may be a fraud or not seeable of their bits per second. Markov process models square measure widespread to represent bits per second of users that is effective for those users whose dealings behaviors square measure stable comparatively. However, with the event and popularization of on-line looking, it's a lot of convenient for users to consume via the net that diversifies the dealings behaviors of users. Therefore, Markov process models square measure unsuitable for the illustration of those behaviors. During this paper, we have a tendency to propose logical graph of BP (LGBP) that may be a total order-based model to represent the relation of attributes of dealings records. Supported LGBP and users dealings records, we are able to cipher a path-based transition chance from AN attribute to a different one. Here we are able to find Face by mistreatment viola jones and LBP acknowledge formula for face detection as we use invisible keyword sequence for authentication of OTP. The keyword sequence modification when. At constant time, we have a tendency to outline. A data entropy-based diversity constant so as to characterize the variety of dealings behaviors of a user. We have a tendency to additionally track fraud user with location by mackintosh address of the user laptop portable computer} or computer that have last dealings with success. Additionally, we have a tendency to outline a state transition chance matrix to capture temporal options of transactions of a user. Consequently, we are able to construct a BP for every user so use it to verify if AN incoming dealings may be a fraud or not. Our experiments over a true information set illustrate that our methodology is healthier than 3 progressive ones

Behavior profile (BP), e-commerce security, Face Detection, Invisible Keyboard Sequence, fraud detection, online transaction

"Survey On Credit Card Fraud Detection using Face Authentication", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 5, page no.d857-d861, May-2021, Available :http://www.jetir.org/papers/JETIR2105508.pdf

"Survey On Credit Card Fraud Detection using Face Authentication", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 5, page no. ppd857-d861, May-2021, Available at : http://www.jetir.org/papers/JETIR2105508.pdf