• Login
  • Register
  • Search

Application of multi-source heterogeneous analysis in user behavior prediction

Jianing Fang


This study aims to accurately predict user lifecycle stages and behaviors using multi-source heterogeneous datasets. The core question is how to integrate various user attributes and interactions to effectively predict engagement and behavior patterns. This study develops a
comprehensive predictive model by combining multiple machine learning models to improve accuracy. The approach involves using user demographics, interaction patterns, and feedback characteristics to create separate predictive models, which are then integrated through ensemble learning methods such as stacking. Key performance metrics such as accuracy, precision, recall, and F1 score evaluate the effectiveness
of the model. The findings show that tailoring the user experience based on attributes such as age, gender, location, device type and browsing
patterns can significantly increase engagement and retention. Additionally, advertising strategies tailored to user preferences can increase conversion rates and satisfaction. The combined model outperforms the single model in terms of prediction accuracy and overall performance.


Multi-source Heterogeneous Analysis, Behavioral Prediction, Application

Full Text:


Included Database


[1] Guo, L., Zhang, B. and Zhao, X., 2021. A Consumer Behavior Prediction Model Based on Multivariate Real-Time Sequence Analysis. Mathematical Problems in Engineering.

[2] Wu, L., Zhang, J., Zhang, H. and Weng, H., 2022. Predicting touristic consumer behavior using big data: an integrated model. Journal of Retailing and Consumer Services, 63, p.102726.

[3] Zhang, Y., 2022. Big data analytics for customer behavior analysis in online shopping environments. Information Systems Frontiers, 24(1), pp.55-74.

[4] Safara, F., 2022. A computational model to predict consumer behaviour during COVID-19 pandemic. Computational Economics,

59(1), pp.1525-1538.

[5] Zhou, L., Zhang, Y., and Chen, X., 2021. Consumer behavior in the online classroom: Using video analytics and machine learning

to understand the determinants of engagement. Electronic Commerce Research and Applications, 49, p.101067.

[6] Goel, S., Hofman, J.M., Lahaie, S., Pennock, D.M., and Watts, D.J., 2010. Predicting consumer behavior with web search. Proceedings of the National Academy of Sciences, 107(41), pp.17486-17490.

[7] Duval, K. (2020). When and Why Prediction-Based Appeals Influence Consumer Behavior: The Role of Self-Construal. Doctor of

Philosophy (Business Administration) Thesis, John Molson School of Business, Concordia University, Montreal, Quebec, Canada. Available

at: [Accessed 21 May 2024].

DOI: http://dx.doi.org/10.18686/fm.v9i4.13073