With the improvement of online transaction systems and online shopping platforms, more and more customers choose online purchase. However, because customers and merchants cannot communicate face-to-face, merchants know very little about their customers’ needs and cannot grasp their thoughts in a timely manner. The online system records consumer operations and collects consumer behavior data, making it possible to predict consumers’ buying preferences. This article takes the real unbalance shopping data of the ecommerce platform as the research object, and uses the catboost model to analyze and predict whether consumers will purchase a certain product. The accuracy; precision and some other criterion of the model are given to evaluate the performance of the prediction. A better effect is obtained: the accuracy reach 88.51% in predicting purchase behavior in this data set.
Paper
Full text
Online Purchase Behavior Prediction and Analysis Using Ensemble Learning
Semantic Scholar · Computer Science · 2020
Abstract
With the improvement of online transaction systems and online shopping platforms, more and more customers choose online purchase. However, because customers and merchants cannot communicate face-to-face, merchants know very little about their customers’ needs and cannot grasp their thoughts in a timely manner. The online system records consumer operations and collects consumer behavior data, making it possible to predict consumers’ buying preferences. This article takes the real unbalance shopping data of the ecommerce platform as the research object, and uses the catboost model to analyze and predict whether consumers will purchase a certain product. The accuracy; precision and some other criterion of the model are given to evaluate the performance of the prediction. A better effect is obtained: the accuracy reach 88.51% in predicting purchase behavior in this data set.