Type: Process Essays
Sample donated: Chester Franklin
Last updated: September 28, 2019
hee-commerce platform is a substantial marketplace with a group of persons suchas merchants, customers, banks, and other commercial societies. Hence, thee-commerce system is a very vibrant and voluminous one. One of such system isCredit card payment in online. Useof credit cards for online purchases has significantly increased and it causedan explosion in the credit card fraud. Credit card fraud includes dishonest useof card or account information without the knowledge of the owner; hence it isan act of criminal process.
Currently, the major problem for e-commerce business is thatfraudulent transactions appear more and more similar to genuine ones 1. Generally,in real case, the fraud datasets are extremely skewed and scattered. Hence,statistical fraud detection or simple pattern matching techniques are notefficient to detect fraud. Therefore, execution of effectivefraud detection system becomes crucial for all card issuing systems to avoidtheir losses.
Hidden Markov Model will be used as a key to find outthe fraudulent transaction by using the expenditure profiles of users. It workson the user’s expenditure profiles which can be divided into major three typessuch as 1) Lower profile; 2) Middle profile; and 3) Higher profile 7-8. Forevery credit card, the expenditure profile is different, so it can figure outan inconsistency of user profile and try to find fraudulent transaction.
Itkeeps record of expenditure profile of the card holder with the transactionsthat are done in online. Thus analysis of card holder’s profile will be auseful tool in fraud detection system and it is an assuring way to checkfraudulent transaction, although fraud detection system does not keep recordsof number of purchased goods and categories 2,3. The set of informationcontains expenditure profile of card holder, money spent in every transaction,the last purchase time, category of purchase etc. The main challenge here ishow to improve detection accuracy, the computational capacity of the detectionsystem. This factor has become more and more important with the unpredictablegrowth of trading data. In E-commerce, virtual cards are used more frequentlythan physical cards, which make the payment much easier and create many smallbut frequent transactions. The growing number of users and payment transactionshas brought heavy workloads to these systems.
The speed of new transactionscoming into the system can reach millions per second while the size of storedhistorical transactions can reach several PBs or even EBs. In this case,processing of the detection task with the incoming transactions with a lowdelay is very hard for most traditional systems. According to the recent trends, Big Data technologyseems to be the key of solving the challenge of computational capacity. Thus theproposed fraud detection system has to be implemented in a Big Data tool foranalysing huge data.