基于SEM的B2C电子商务信任评价模型及算法

消费者信任对B2C型电子商务的成功起着非常重要的作用。本文通过结构方程模型(SEM)原理构建了消费者网上信任度指数评估模型,在单位结构变量的约束下,考虑误差方差。推导了应用偏最小二乘(PLS)估计算法的模型最佳迭代初值,提高了计算速度,说明了算法的收敛性。由此模型可以分析评价指标体系的各结构变量之间、结构变量与观测变量之间的相关关系；文中进一步给出了电子商务信任度指数计算公式,从而可以更有效地分析消费者网上交易的信任度,以便采取有效措施促进电子商务的发展。

Evaluation for Consumer Online Trust Based on Structural Equation Modeling and Path Analysis

E-commerce success,especially in the B2C area,is deter- mined in part by whether consumers trust sellers and products they cannot see or touch,and electronic systems with which they have no previous experience.This paper constructs the evaluation of con- sumer online trust index model based on Structural Equation Model- ing(SEM).The best iterative initial values for Partial Least Square (PLS)estimation algorithm was put forward,which can enhance the speed of computation.With our model,the relationship of construc- tion variables in consumer online trust evaluation indexes system can be analyzed,as well as the relationship between the construction and observation variables,also formula to calculate the electronic com- merce trust index is provided in the paper.Consequently,consumer online trust can be analyzed efficiently,and efficient measures can be adopted to improve the consumer online trust,so that EC can devel- ops more quickly.