Main Article Content
Electronic commerce or e-commerce is a business model that lets companies and persons over the internet buy and sell anything. Recently, in the age of the Internet and forwarding to E-commerce, lots of data are stored and transferred from one location to another. Data that transferred can be exposed to danger by fraudsters. There is a massive increase in fraud which is leading to the loss of many billions of dollars worldwide every year. There are various modern ways of detecting fraud that is regularly proposed and applied to several business fields. The main task of Fraud detection is to observe the actions of tons of users to detect unwanted behavior. To detect these various kinds, data mining methods & machine learning to have been proposed and implemented to lessen down the attacks. A long time ago, many methods are utilized for fraud detection system such as Support Vector Machine (SVM), K-nearest Neighbor (KNN), neural networks (NN), Fuzzy Logic, Decision Trees, and many more. All these techniques have yielded decent results but still needing to improve the accuracy even further, by developing the techniques themselves or by using a hybrid learning approach for detecting frauds. In this paper, a review to describe the latest studies on fraud detection in e-commerce between (2018-2020), and a general analysis of the results- achieved and upcoming challenges for further researches. This will be useful for giving us complete visualization about how can we present the most suitable, most accurate methods for fraud detection in e-commerce transactions.