A Fuzzy-Logic Based Trust Model and its Optimization for e-Commerce

The emerging of the e-Commerce provides more and more businesses opportunities to vendors and manufacturers. However, the expeditious evolution of e-Commerce has also caused challenging security issues. To protect vendors and consumers from being victimized, various trust models have been used in e-Commerce practices. Nevertheless, a strict verification and authentication process may pose unnecessarily heavy cost to the vendor. This paper presents a solution to reduce costs for vendors. A framework that consists of three functional blocks is proposed. These are Fuzzy Trust Module, Cost Evaluation Module, and Parameter Tuning Module. The Fuzzy Trust Module makes trust decisions based on inputs such as the customer’s credit history and the price of the goods. The Cost Evaluation Module takes the output of Fuzzy Trust Module, as well as other information, to evaluate the normalized cumulative cost of the transactions. Based on the cost, the Parameter Tuning Module optimizes the performance of the system by adjusting the structural parameters of the Fuzzy Trust Module. With this new approach, more realistic trust decisions can be reached.