Affiliation:
1. School of Digital Commerce, Beijing Information Technology College, Beijing 100018, China
Abstract
Due to the low efficiency of traditional data analysis methods for massive e-commerce data analysis, an e-commerce data analysis and prediction method based on the GBDT deep learning model was proposed. Purchase behavior is divided into another category, which transforms the problem of e-commerce data analysis and prediction into a binary classification problem. At the same time, we extract 107 features that can reflect the user behavior and construct the GBDT model. The characteristics include counting class, sorting class, time difference class, conversion rate class, and so on. It follows from the above that the analysis and prediction of e-commerce data are realized. In addition, the results show that when the learning rate of GBDT model parameters is 0.05, the number of basic learners is 200, the tree depth is 20, the threshold is 0.5, the model prediction effect is best, and the F1 value can reach 0.12. Compared with the traditional prediction model based on logistic regression and neural network, the proposed GBDT model is more suitable for e-commerce data analysis and prediction.
Subject
Computer Science Applications,Software
Reference25 articles.
1. Multicollinearity in logistic regression models[J];B. E. Ozgur;Anesthesia & Analgesia,2021
2. Advanced Statistics: Multiple Logistic Regression, Cox Proportional Hazards, and Propensity Scores
3. Digital document analytics using logistic regressive and deep transition-based dependency parsing;D. Rekha;The Journal of Supercomputing,2021
4. Indian stock markets data analysis and prediction using macroeconomics indictors in machine learning;J. Singh;International Journal of Innovative Technology and Exploring Engineering,2020
5. A model-based approach of data analysis and prediction in chronic kidney diseases (CKD);F. Halawa
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献