A Dual Mode Risk Analysis Model For Efficient Cross Border Transaction Using Big Data

Abstract

Increasing online transaction and commercial activities stimulates the rate of online frauds from both sides of E-commerce. However, the researchers focused on specific side of commercial action and designs solutions to making decision from their side. This challenges the trust of intermediate platforms like Amazon. To handle this issue, a dual model risk analysis model (DMRAM) is presented in this article to support cross border transaction. With the big data given, the data has been normalized according to the feature and values in the traces. The method analyzes the trust of both seller and consumer in various constraints. Towards trust analysis of seller, the method estimates Delivery Support (DS) according to the behavior of seller in sending exact product and post service provided. Similarly, the method analyzes the trust of consumer according to Payment Trust Analysis which computes payment support (PS) according to different factors like behavior of transaction, behavior of goods handling. Using both the analysis results, the method computes E-commerce support (EcS), based on which the selection of seller has been allowed. The proposed method improves the performance of cross border transaction with big data