A Big Data-based Prediction Model for Purchase Decisions of Consumers on Cross-border E-commerce Platforms

Abstract

In recent years, cross-border e-commerce platforms have become an important way for Chinese consumers to buy overseas products. This paper aims to find out the main influencing factors of the consumer behavior on cross-border e-commerce platforms, and predict the purchase decisions of food product on these platforms. Firstly, twelve factors that may affect the purchase decisions of consumers on cross-border e-commerce platforms were selected, and subjected to big data analysis. Seven of them were found to have a significant impact on consumer behavior on the said platforms. Next, a multilayer perceptron (MLP) was constructed to evaluate the importance of each influencing factor to the purchase decisions. The fuzzy weights of the most important factors were determined by an improved frequent-pattern (FP) growth algorithm. Finally, a purchase decision prediction model was established for consumers on cross-border e-commerce platforms, and successfully applied to predict the purchase decisions over 6 categories of products on such platforms.