An xgboost algorithm for predicting purchasing behaviour on e-commerce platforms

Abstract

To improve and enhance the predictive ability of consumer purchasing behaviours on e-commerce platforms, a new method of predicting purchasing behaviour on e-commerce platforms is created in this paper. This study introduced the basic principles of the XGBoost algorithm, analysed the historical data of an e-commerce platform, pre-processed the original data and constructed an e-commerce platform consumer purchase prediction model based on the XGBoost algorithm. By using the traditional random forest algorithm for comparative analysis, the K-fold cross-validation method was further used, combined with model performance indicators such as accuracy rate, precision rate, recall rate and F1-score to evaluate the classification accuracy of the model. The characteristics of the importance of the results were found through visual analysis. The results indicated that using the XGBoost algorithm to predict the purchasing behaviours of e-commerce platform consumers can improve the performance of the method and obtain a better prediction effect. This study provides a reference for improving the accuracy of e-commerce platform consumers' purchasing behaviours prediction, and has important practical significance for the efficient operation of e-commerce platforms.