A Study On Cross-border E-commerce Recommendation System Based On Collaborative Filtering

As a new industry in e-commerce,cross-border e-commerce has dramatically expanded its data scale as e-commerce,and users are facing an increasingly serious problem of “information overload”.As an effective means to solve this problem,the ecommerce recommendation system has achieved certain results in both academia and business.However,because cross-border e-commerce involves the export and import of goods,it is affected by many policies and regulations,resulting in some special requirements for the recommendation system,which makes the traditional collaborative filtering recommendation algorithm less effective for the cross-border e-commerce recommendation system.This thesis first summarizes and combs the basic theory of the existing collaborative filtering recommendation system.On this basis,it combines the user preferences to commodity attributes and contextualized user preferences to meet the system requirements of the cross-border e-commerce recommendation system.This thesis firstly reviews the e-commerce recommendation system based on the existing research and sorts out the main points of constructing the e-commerce recommendation system.Then two common recommendation algorithms are introduced,and also the advantages and disadvantages of the two are algorithms analyzed.Meanwhile,it also summarizes the rating methods and evaluation indicators of the e-commerce recommendation system,and also gives some calculation methods for evaluation indicators.Then a detailed description of the traditional collaborative filtering recommendation algorithm and analysis of its advantages and disadvantages are given.According to the actual situation of the enterprise and national policies,the thesis analyzes system requirement and obtains a series of special needs of the cross-border ecommerce industry.Then a collaborative filtering recommendation algorithm based on commodity attributes and contextualized user preferences is proposed to meet the system requirements,and the system framework and algorithm flow are given.Finally,this thesis uses a cross-border e-commerce enterprise order data set to analyze the improved algorithm proposed.Compared with the traditional collaborative filtering recommendation algorithm,the improved algorithm reduces the impact of data sparsity.The experiment also verifies that the improved algorithm has better recommendation effect than the traditional collaborative filtering.