Research And Design Of Intelligent E-Commerce Systems Based On Retail

As an important marketing tool for the E-Commerce web sites, the recommender system provides customers with valuable advices from millions of item information, so as to help promote the marketing performance of the web sites. With the progress of the Internet and the computer technology, the E-Commerce recommender system receives deeper research and development which make it produce more intelligent and more personal services. Meanwhile, the scale of E-Commerce is developing so fast that the recommender system is facing a serial of challenges. This paper discusses a few sticking points of the recommender system such as the arithmetic design and its structure.First, the basic theories of the recommender system are introduced, including its background of arising, conception, effect, inputting module, outputting module, some widely used recommending technologies, as well as the hotspots in this field.Second, this paper presents kinds of recommending technologies respectively including information filtering technology, data mining technology, Horting Graph technology etc.and emphasizes the information filtering technology which includes content filtering and collaborative filtering. We analyse the signification and the arithmetic of these two information filtering technologies, point out their merit and defect respectively, and then discuss the notion of combining them in the field of recommending the culture items such as movies,music,etc.as this paper's basic springboard.Third, According to the sparsity of the data and real time problem, on a base of the traditional collaborative filtering technology we bring forward user cooperation recommendation mechanism based on interest degree vector model. We describe the principle and procedure of this mechanism taking the example of movie recommending. We use the data provided on MovieLens to carry out the recommending experiment and analyse the Mean Absolute Error. The experiments show that this method has better precision than the traditional collaborative filtering.Fourth, on a base of recommendation method based on interest degree vector model, the value of customers' demographic information for reference is added into the module, which helps to make the recommending result more exact and solve the new customer problem in the recommender system.Finally, on the basis of the study mentioned above, the framework of personalized E-Commerce recommender system based on the customers' interests and cooperations is described, and we reasonably define the boundary and applying fields of the system.The research work of this thesis integrates very tightly with the switching of information between users, skillfully combines the content of commodity characteristics and users' demographic characteristics, better resolve the sparsity of the data, real time and the new customer problem in existing recommender system. Recommendation system which this article studies is suitable for recommendation activities of the field through cultural commodity which is not easy to describe exactly as content, can be used as a subsystem to run for large-scale recommender systems.