The Adoption Factors Of E-Commerce Recommendation System

The development of Internet has deepened the impact of the information age. But in e-commerce environment, it is difficult for customers to find the product they need. E-commerce recommendation system can eliminate the effect of information overload and help users get information they want. Its great value has been widely recognized in a lot of areas. Like other adoption researches, the adoption of e-commerce recommendation system is also subject to various factors. However, the research on the users' adoption of the recommendation system is relatively rare, and there are no systematic results. And domestic research in this area is basically blank. Therefore, it is need to explore what factors affect the system using, and how these factors affect. The goal of this paper is to find these factors and improve the user's intention to adopt recommend system. Then it can help the websites increase their sales and users experience.This paper firstly explains the content of e-commerce recommendation system. Based on the detailed analysis of adoption process of recommendation system, the paper presents six external variables affecting users' adoption, which include the accuracy of recommended results, the diversity of recommended results, user interaction, the system interface, the system interaction and the transparency of recommendation. According to mechanism analysis of these variables, the paper derives ten hypotheses and constructs the hypotheses model to explain users' adoption of recommendation system in e-commerce environment.This paper collects 302 data in the form of internet survey. On this basis, the paper evaluates the recommendation system adoption model using the path analysis principle, and explores the relationship between external and internal variables included by the model. Finally, according to the analysis results and specific factors, the paper analyses and discusses the research results of this paper from three aspects including the relationship between perceived usefulness and accuracy of recommended results, user interaction, system interaction; the relationship between system interface, system interaction, transparency of recommendation and perceived ease of usefulness; the relationship between perceived usefulness, perceived ease of usefulness and adoption intention of e-commerce recommendation system, and proposes the suggestion for improving the adoption of e-commerce recommendation system.