Business User Portrait Modeling and Clustering Analysis Under The Background of Big Data

摘要

Based on the data of a B2C e-commerce platform, this paper studies and applies the user profile modeling. We focus on business users, use statistical analysis, clustering and other methods to label users, design and implement a user profile system based on text mining. The text preprocessing of user data is completed by word segmentation technology and feature selection. LDA topic model is used to assign topics for each query word, so that the query word and its topic are put into the neural network model to learn the topic vector. Finally, the experiments are performed to verify the accuracy of the system and the results show that the classification accuracy of the model is higher than that of the word vector model.