Predicting User Behavior Based on Data Science Methods
Keywords:
Data Science, user behavior, prediction model, XGBoost, e-commerce, machine learning.Abstract
This paper explores the problem of predicting user behavior using Data Science methodologies. A real-world dataset related to an e-commerce platform was selected for the study. The process included data preprocessing, feature extraction, and the evaluation of four machine learning models: Logistic Regression, Random Forest, XGBoost, and MLP Neural Network. Among these, the XGBoost model achieved the highest accuracy and F1-score. Key influential features identified include the number of product views, instances of items being added to the cart, and session duration. The study demonstrates the effectiveness of Data Science approaches in optimizing business decisions by predicting the likelihood of user purchases in advance.
References
Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd ed.). O’Reilly Media.
Kaggle. (2020). E-Commerce Behavior Data from Multi-category Store. https://www.kaggle.com/datasets/mkechinov/ecommerce-behavior-data-from-multi-category-store
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An Introduction to Statistical Learning with Applications in R (2nd ed.). Springer. https://www.statlearning.com/
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
Brownlee, J. (2016). Imbalanced Classification with Python. Machine Learning Mastery. https://machinelearningmastery.com/what-is-imbalanced-classification/
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Zhang, Y., & Pennacchiotti, M. (2013). Predicting Purchase Decisions in E-Commerce Using Social Media. Proceedings of the 22nd ACM International Conference on World Wide Web, 1521–1532. https://doi.org/10.1145/2488388.2488497
