Predictive Analysis of User Purchase Behavior based on Machine Learning

Abstract

In corporate customer management, companies are required to evaluate the costs and benefits of investment expenditures and determine the optimal resource allocation for marketing and sales activities within a period. Understanding the buying behavior of customers in the future is a key driving force for the sales and marketing departments to effectively allocate resources. This paper proposes a combined prediction model that uses the Stacking method to integrate multiple decision tree models to predict whether users will buy in the future and their specific purchase time. The model uses the idea of stacking model fusion to fuse the prediction results of three different integrated decision tree models of Light GBM, XG Boost, and Random Forest, and then uses a simple logistic regression classification model and a linear regression model to predict separately based on the fused prediction results Whether the user will buy in the future and the specific time of purchase. In addition, in this study, we used real retail sales data to evaluate the predictive performance of the proposed method.