E-commerce User Recommendation Algorithm Based on Social Relationship Characteristics and Improved K-Means Algorithm

Abstract

AbstractIn the era of the Internet, information data continue to accumulate, and the explosive growth of network information explosion leads to the reduction of the accuracy of users’ access to information. To enhance the user experience and purchasing desire of e-commerce users, a e-commerce user recommendation algorithm based on social relationship characteristics and improved K-means algorithm is proposed. It combines the Automatic Time Division Dynamic Topic Model based on adaptive time slice division for building a strength calculation model in view of the characteristics of social relations. Then, it proposes an e-commerce user recommendation algorithm in view of the improved K-means algorithm to improve the accuracy of topic feature extraction and user recommendation. The experiment illustrates that there is no fluctuation in the clustering function of the improved K-means algorithm, and the highest, lowest, and average accuracy remain consistent under the three datasets, with average accuracy of 78.9%, 84.5%, and 95.9%, respectively. The community discovery-based friend recommendation algorithm presented in the study has the highest accuracy, illustrating that improving the K-means algorithm can further improve recommendation accuracy. The accuracy of the feature extraction method in view of alternative cost is 0.63, which improves the accuracy by about 9%. The results indicate that this study can provide technical support for user recommendations on e-commerce platforms.