[Retracted] A Social-aware and Mobile Computing-based E-Commerce Product Recommendation System
Table 1
Comparison of the main recommended technologies.
ā
Advantage
Shortcoming
Collaborative filtering technology
Discover new and different interests and do not depend on domain knowledge. With the passage of time and the accumulation of data, the effect is getting better and better. The recommendation process has a high degree of personalization and automation and can deal with complex unstructured objects
There are typical problems such as scalability, sparsity and cold start, and the recommendation quality depends on the historical data set
Association rule mining
Can discover new and different points of interest, independent of domain knowledge
Rule extraction is difficult and time-consuming, and the degree of personalization is low
Knowledge experience-based approach
It can consider nonproduct attributes, reflect user needs, and make up for the lack of user knowledge and experience
Knowledge and experience are difficult to obtain, and recommendation is static