An improved deep forest model for prediction of e-commerce consumers’ repurchase behavior

• Published in: PloS one Vol. 16; no. 9; p. e0255906
• Main Authors: Zhang, Weiwei, Wang, Mingyan
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 20.09.2021; Public Library of Science (PLoS)
• Subjects: Accuracy; Analysis; Big Data; Biology and Life Sciences; Computer and Information Sciences; Consumer behavior; Consumer preferences; Consumers; Datasets; Ecology and Environmental Sciences; Electronic commerce; Engineering; Evaluation; Experiments; Influence; Internet; Machine learning; Neural networks; Physical Sciences; Prediction models; Psychological aspects; Research and Analysis Methods; Retailing industry; Social Sciences; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0255906

As the Internet retail industry continues to rise, more and more consumers choose to shop online, especially Chinese consumers. Using consumer behavior data left on the Internet to predict repurchase behavior is of great significance for companies to achieve precision marketing. This paper proposes an improved deep forest model, and the interactive behavior characteristics of users and goods are added into the original feature model to predict the repurchase behavior of e-commerce consumers. Based on the Alibaba mobile e-commerce platform data set, first construct a feature engineering that includes user characteristics, product characteristics, and interactive behavior characteristics. And then use our proposed model to make predictions. Experiments show that the model’s overall performance with increased interactive behavior features is better and has higher accuracy. Compared with the existing prediction models, the improved deep forest model has certain advantages, which not only improves the prediction accuracy but also reduces the cost of training time.